© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 89489
    Prev
    Next
    INDEX
    Explanations

    _t

    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
     convex
    -0.07
    _feedback
    -0.07
    钎
    -0.07
     tung
    -0.07
    .Rollback
    -0.07
    //
    -0.07
    是一项
    -0.07
    (alert
    -0.07
    _tooltip
    -0.07
    뒤
    -0.07
    POSITIVE LOGITS
     wander
    0.08
     coordinator
    0.07
    codes
    0.07
    ologists
    0.07
     Produto
    0.07
    =======
    0.07
     propag
    0.07
    igrated
    0.07
     pictured
    0.06
    filePath
    0.06
    Activations Density 0.002%

    No Known Activations