© 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. 20-TRANSCODER-HP
    7. 62886
    Prev
    Next
    INDEX
    Explanations

    scientific/technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æľīåı¯èĥ½
    -0.36
     potential
    -0.30
     Potential
    -0.30
    åĢĻéĢī
    -0.30
    çĸijä¼¼
    -0.30
    çļĦåı¯èĥ½æĢ§
    -0.29
    potential
    -0.29
     potentially
    -0.29
    isto
    -0.28
    æ½ľåĬĽ
    -0.28
    POSITIVE LOGITS
    èħĻ
    0.31
    ยà¸Ńà¸Ķ
    0.27
    èĦį
    0.27
     LPARAM
    0.27
     Covered
    0.27
    ä¸Ģç«Ļ
    0.25
    æīĵ交éģĵ
    0.25
     famously
    0.24
    ä¸ĢæŃ¥æŃ¥
    0.24
    ÅĤoÅĽÄĩ
    0.24
    Activations Density 28.742%

    No Known Activations