© 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. 9530
    Prev
    Next
    INDEX
    Explanations

    code/running snippets

    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
     Tues
    -0.28
    andle
    -0.26
    cem
    -0.26
    ceased
    -0.26
     Sunday
    -0.26
     Tuesday
    -0.24
    rogen
    -0.24
    åĴĮæĶ¯æĮģ
    -0.24
     ePub
    -0.24
    è¶Ĭ
    -0.23
    POSITIVE LOGITS
    eli
    0.27
    ODO
    0.25
    ä½ľçĶ¨
    0.24
    .erase
    0.24
    å¸Ĥåľºç«ŀäºī
    0.24
    çļĦåIJĦç§į
    0.24
     Duo
    0.23
    æľīä¸Ģå®ļçļĦ
    0.23
    ç»ıå¼Ģ
    0.23
    mot
    0.23
    Activations Density 0.034%

    No Known Activations