© 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. 19-RESID-POST-AA
    11. 70844
    Prev
    Next
    INDEX
    Explanations

    Numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .drawRect
    -0.08
    óc
    -0.07
    كات
    -0.07
    _Cell
    -0.07
     Exodus
    -0.07
    צה
    -0.07
    ày
    -0.07
    odb
    -0.07
    هد
    -0.07
    igate
    -0.07
    POSITIVE LOGITS
    _VOID
    0.07
     Lack
    0.07
    不负
    0.07
     padr
    0.07
    Le
    0.07
    `.↵
    0.07
    /gr
    0.06
     yaptı
    0.06
    �
    0.06
     хр
    0.06
    Activations Density 0.056%

    No Known Activations