© 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. 7-RESID-POST-AA
    11. 11382
    Prev
    Next
    INDEX
    Explanations

    Egypt

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    老
    -0.08
     Kết
    -0.07
     да
    -0.07
    ato
    -0.07
    联
    -0.07
    _Ad
    -0.07
     Ages
    -0.07
     impacted
    -0.07
    otate
    -0.07
     kết
    -0.07
    POSITIVE LOGITS
    鲂
    0.08
    精益求精
    0.08
    .Exists
    0.07
    望去
    0.07
     HEIGHT
    0.07
     toolStrip
    0.07
     protesters
    0.07
    .getOutputStream
    0.07
    .requireNonNull
    0.06
    raphics
    0.06
    Activations Density 0.013%

    No Known Activations