© 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. 59373
    Prev
    Next
    INDEX
    Explanations

    circle of

    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
    恶心
    -0.07
    峿
    -0.07
    👅
    -0.07
     getById
    -0.07
    WXYZ
    -0.07
    🐀
    -0.07
    阌
    -0.07
     cumshot
    -0.07
     URLSession
    -0.07
    词
    -0.07
    POSITIVE LOGITS
    沙漠
    0.08
     advisor
    0.07
    co
    0.07
     districts
    0.07
    pit
    0.07
     cop
    0.07
     stained
    0.07
     survey
    0.07
    _smooth
    0.07
    ,a
    0.07
    Activations Density 0.076%

    No Known Activations