© 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. 106925
    Prev
    Next
    INDEX
    Explanations

    legal/scientific references

    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
    车ç«Ļ
    -0.28
    æĭ¿åĩº
    -0.24
    æľīä»Ģä¹Ī
    -0.24
     Forex
    -0.24
    andle
    -0.24
    abeled
    -0.23
    AMY
    -0.23
    ä»Ģ麽
    -0.23
    ãģ©ãĤĵãģª
    -0.23
    anches
    -0.23
    POSITIVE LOGITS
    èĨı
    0.29
    表éĿ¢ä¸Ĭ
    0.27
     persisted
    0.26
    isu
    0.26
    å¹´ä¸ĬåįĬå¹´
    0.25
    velle
    0.25
     persist
    0.24
    tru
    0.24
    persistent
    0.24
    åħ¨åĽ½äººæ°ij
    0.24
    Activations Density 0.340%

    No Known Activations