© 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. 19-TRANSCODER-HP
    7. 9426
    Prev
    Next
    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     SR
    -0.29
    ä¸į代表
    -0.29
    ismatic
    -0.28
    ometers
    -0.28
    SR
    -0.28
     ust
    -0.26
    ipline
    -0.26
    æŀķ头
    -0.25
    èĥ½åľ¨
    -0.25
     Strat
    -0.25
    POSITIVE LOGITS
     favourable
    0.28
     favour
    0.28
    =cut
    0.26
    çĶ©
    0.26
     HOLD
    0.24
    shed
    0.24
    åįģæĿ¡
    0.24
    angi
    0.24
    hold
    0.24
     getObject
    0.24
    Activations Density 0.057%

    No Known Activations