© 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. 11-RESID-POST-AA
    11. 58687
    Prev
    Next
    INDEX
    Explanations

    size

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bölgesinde
    -0.07
     pessim
    -0.06
     saying
    -0.06
     devout
    -0.06
     Column
    -0.06
     QSql
    -0.06
     disproportionate
    -0.06
    -negative
    -0.06
    뼛
    -0.06
     legal
    -0.06
    POSITIVE LOGITS
    iske
    0.07
    Custom
    0.07
    ompson
    0.07
    <|im_start|>
    0.07
     Feedback
    0.07
    是什么
    0.07
    sgiving
    0.07
    習
    0.07
    0.07
    tı
    0.06
    Activations Density 0.020%

    No Known Activations