© 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. 44230
    Prev
    Next
    INDEX
    Explanations

    pathfinding code

    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_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
    askets
    -0.07
    ATORS
    -0.07
     MANUAL
    -0.07
    copies
    -0.07
    CUSTOM
    -0.07
    adiens
    -0.07
    dale
    -0.07
    xdc
    -0.07
    -maker
    -0.07
    olls
    -0.07
    POSITIVE LOGITS
     várias
    0.07
    .addSubview
    0.07
     Buenos
    0.07
    ⵖ
    0.07
    -feira
    0.07
    הזד
    0.07
     vielleicht
    0.07
     решил
    0.06
    ierrez
    0.06
    disposed
    0.06
    Activations Density 0.019%

    No Known Activations