© 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. 9442
    Prev
    Next
    INDEX
    Explanations

    job titles/roles

    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
    ded
    -0.29
    ä»ĸè¿ĺ
    -0.26
    wig
    -0.26
    bases
    -0.25
    æ±Ł
    -0.25
    season
    -0.25
    è¶ĬæĿ¥è¶Ĭé«ĺ
    -0.25
    ä¹Łè¶ĬæĿ¥è¶Ĭ
    -0.24
    ủng
    -0.24
    æĦŁåħ´è¶£
    -0.23
    POSITIVE LOGITS
     mão
    0.28
     hand
    0.27
    æīĭ
    0.27
     HAND
    0.25
    icamente
    0.25
     goalkeeper
    0.24
    icky
    0.24
    çĿ¡çľł
    0.24
    ody
    0.24
     Maher
    0.24
    Activations Density 0.038%

    No Known Activations