© 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. 64743
    Prev
    Next
    INDEX
    Explanations

    Numbers and periods

    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
    Negative Logits
    éĻIJéĩı
    -0.28
    fits
    -0.25
     LogManager
    -0.25
    ä¸įè¶ħè¿ĩ
    -0.25
    åĮħ容
    -0.24
    _amt
    -0.24
    ä¸ĬéĻIJ
    -0.24
    limit
    -0.24
     Fits
    -0.24
    çĿĢæĢ¥
    -0.24
    POSITIVE LOGITS
    å¼Ģå§ĭ
    0.33
     minimum
    0.33
    æľĢå°ı
    0.30
     starting
    0.30
     Minimum
    0.29
    éĸĭå§ĭ
    0.29
    æľĢä½İ
    0.28
    å¹´å¼Ģå§ĭ
    0.28
    ä¸įå¤Ł
    0.28
    å·²ç»ıå¼Ģå§ĭ
    0.28
    Activations Density 53.228%

    No Known Activations