© 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. 142423
    Prev
    Next
    INDEX
    Explanations

    healthcare

    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
    -Cs
    -0.28
    ç¼ĸ
    -0.26
    åĩºåĽ½çķĻåѦ
    -0.25
     lack
    -0.25
    è´§
    -0.25
    Saturday
    -0.24
    oll
    -0.24
    æļĤç¼ĵ
    -0.24
     unre
    -0.24
    anden
    -0.24
    POSITIVE LOGITS
    ãģ§ãģĻãģĭãĤī
    0.29
    udad
    0.28
    esome
    0.26
    æĬ¥åijĬæĺ¾ç¤º
    0.26
    大家åĪĨ享
    0.26
    åIJįåı«
    0.25
    inesis
    0.25
    ittle
    0.25
    å£°éŁ³
    0.25
     Glück
    0.25
    Activations Density 6.727%

    No Known Activations