© 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. 106954
    Prev
    Next
    INDEX
    Explanations

    Various written content

    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
    lopedia
    -0.29
    常年
    -0.28
     handbook
    -0.28
     yeti
    -0.28
     Encyclopedia
    -0.28
     FAQ
    -0.28
     encyclopedia
    -0.28
    entic
    -0.27
    æīĭåĨĮ
    -0.27
    eller
    -0.27
    POSITIVE LOGITS
     Ded
    0.31
     Dou
    0.31
     Received
    0.30
    Subset
    0.29
     ded
    0.28
    翻身
    0.28
    è¥ŀ
    0.26
    ç¿»
    0.25
     Turning
    0.25
     deduction
    0.25
    Activations Density 43.633%

    No Known Activations