© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 88676
    Prev
    Next
    INDEX
    Explanations

    Connecting words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uhl
    -0.29
    xEB
    -0.28
    abad
    -0.27
    ëŀ¨
    -0.27
    ream
    -0.26
    UBY
    -0.26
     COPY
    -0.26
     EAST
    -0.25
    urg
    -0.25
    rapy
    -0.25
    POSITIVE LOGITS
    umper
    0.28
    æľĢæĸ°çļĦ
    0.28
    好çļĦ
    0.27
    over
    0.27
     over
    0.27
    its
    0.26
    æѤæĸĩ
    0.26
    lier
    0.26
     overs
    0.25
    erto
    0.25
    Activations Density 0.006%

    No Known Activations