© 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. 99074
    Prev
    Next
    INDEX
    Explanations

    famous or well-known

    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
    Negative Logits
    åĿļ强
    -0.31
    äºĭä¸ļ
    -0.25
    稼
    -0.25
    é«ĺ度éĩįè§Ĩ
    -0.24
    iled
    -0.24
    åIJİéĿ¢
    -0.24
    è¾Ľåĭ¤
    -0.24
    ç¶
    -0.24
     find
    -0.24
     sık
    -0.24
    POSITIVE LOGITS
    feit
    0.29
    för
    0.27
    /opt
    0.27
    iode
    0.27
    åģļ梦
    0.26
    UDO
    0.25
    ä¸įåħį
    0.24
    bow
    0.24
    ragon
    0.24
    .aw
    0.24
    Activations Density 0.006%

    No Known Activations