© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 64304
    Prev
    Next
    INDEX
    Explanations

    are

    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
    å®Įåħ¨
    -0.39
     completely
    -0.35
    å®Įåħ¨æ²¡æľī
    -0.34
     entirely
    -0.33
    å®Įåħ¨æĺ¯
    -0.33
    å½»åºķ
    -0.30
     completamente
    -0.29
     perfectly
    -0.29
     outright
    -0.28
     perfect
    -0.28
    POSITIVE LOGITS
    omore
    0.30
    æŁ¥çľĭæĽ´å¤ļ
    0.29
    æĽ´å¤ļçļĦ
    0.27
    综åIJĪä½ĵ
    0.27
     Keeper
    0.27
     warmer
    0.27
    æķıæĦŁ
    0.26
     longer
    0.26
    æĽ´å¤§çļĦ
    0.26
    ìĽĢ
    0.26
    Activations Density 39.419%

    No Known Activations