© 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. 11-RESID-POST-AA
    6. 92935
    Prev
    Next
    INDEX
    Explanations

    vehicles

    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
     ACT
    -0.07
    矼
    -0.07
     funds
    -0.07
    haus
    -0.07
     DISPATCH
    -0.07
    _mp
    -0.07
    (TRUE
    -0.06
     Cups
    -0.06
     גבוה
    -0.06
    uffix
    -0.06
    POSITIVE LOGITS
    /close
    0.07
    _FLOW
    0.06
     suction
    0.06
    createdAt
    0.06
     disturbed
    0.06
    DEM
    0.06
    缆
    0.06
     conventional
    0.06
     concerned
    0.06
     concat
    0.06
    Activations Density 0.037%

    No Known Activations