© 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 EvalsExportsAPI 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. 63274
    Prev
    Next
    INDEX
    Explanations

    technical programming identifiers and API/class names, especially CamelCase or concatenated components in code and documentation.

    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
    -Un
    -0.08
    Such
    -0.08
    características
    -0.07
     backgroundColor
    -0.07
     ';↵
    -0.07
    ():
    -0.07
    ************************************************
    -0.07
    㳘
    -0.07
    Gs
    -0.07
     setEmail
    -0.07
    POSITIVE LOGITS
     manpower
    0.07
    בת
    0.07
     prized
    0.07
    香气
    0.07
    ຜ
    0.07
     airborne
    0.07
    펙
    0.07
     تح
    0.07
     서로
    0.07
     kter
    0.07
    Activations Density 0.277%

    No Known Activations