© 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. 7630
    Prev
    Next
    INDEX
    Explanations

    Renaming/rebranding

    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
     Developed
    -0.07
     shape
    -0.07
    ﯶ
    -0.07
     trophies
    -0.07
    陌生人
    -0.07
    _boxes
    -0.06
     "#
    -0.06
     formulas
    -0.06
    师事务
    -0.06
     spaces
    -0.06
    POSITIVE LOGITS
    ŗ
    0.07
    حت
    0.07
     VALID
    0.07
     поб
    0.07
    $total
    0.07
    ٪
    0.07
     slew
    0.07
    [selected
    0.07
    pur
    0.06
     доволь
    0.06
    Activations Density 0.044%

    No Known Activations