© 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. 81672
    Prev
    Next
    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash

    polite second-person requests asking the assistant to provide help, advice, explanations, or to perform a task.

    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
     Arkadaş
    -0.08
    伙
    -0.07
    楒
    -0.07
    힝
    -0.07
     merch
    -0.07
    .pageSize
    -0.07
    栴
    -0.07
    事業
    -0.07
    얔
    -0.07
    岠
    -0.07
    POSITIVE LOGITS
     BinaryTree
    0.08
     clos
    0.08
     Clo
    0.07
    -N
    0.07
     Prot
    0.07
     Offices
    0.07
     Minister
    0.07
    ordial
    0.07
    _Off
    0.07
     Behind
    0.07
    Activations Density 0.026%

    No Known Activations