© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 4607
    Prev
    Next
    INDEX
    Explanations

    Instructions and explanations

    np_max-act · gemini-2.0-flash

    structured, procedural formatting such as step-by-step instructions, numbered/bulleted lists, section headings, and code block scaffolding

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    selectedIndex
    -0.10
     hObject
    -0.07
     développement
    -0.06
    .getResource
    -0.06
     librarian
    -0.06
    酥
    -0.06
    традицион
    -0.06
     tandem
    -0.06
     apache
    -0.06
     mysqli
    -0.06
    POSITIVE LOGITS
     LGBTQ
    0.07
     الا
    0.06
    Hint
    0.06
    äß
    0.06
    /INFO
    0.06
     trap
    0.06
     molt
    0.06
    ]};↵
    0.06
     No
    0.06
     sudden
    0.06
    Activations Density 1.270%

    No Known Activations