© 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. 129038
    Prev
    Next
    INDEX
    Explanations

    Copyright/legal texts

    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
    çļĦç«ŀäºī
    -0.39
    è´ŁéĿ¢
    -0.35
    ç«ŀäºī
    -0.35
     confrontation
    -0.34
     confront
    -0.34
    åİĭè¿«
    -0.31
    åİĭåĪ¶
    -0.31
     competition
    -0.31
    è¿«
    -0.30
    ç½ļ
    -0.30
    POSITIVE LOGITS
    æĶ¯æĮģ
    0.33
    çļĦæĶ¯æĮģ
    0.30
    æĶ¯æı´
    0.30
     comfort
    0.28
     support
    0.28
    åĴĮæĶ¯æĮģ
    0.27
     cosy
    0.27
    å¿ĥæĦı
    0.26
    åıijå±ķ模å¼ı
    0.26
    ãĤµãĥĿãĥ¼ãĥĪ
    0.25
    Activations Density 0.006%

    No Known Activations