© 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. 106971
    Prev
    Next
    INDEX
    Explanations

    2

    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
    ä¸Ģ度
    -0.28
    æľ¬èº«
    -0.25
    åīįéĢĶ
    -0.25
    ä¸ĸ家
    -0.25
    /dist
    -0.24
    å®Ŀ
    -0.24
    è¾ĭ
    -0.24
    GetValue
    -0.23
     minib
    -0.23
     ÑĢеж
    -0.23
    POSITIVE LOGITS
     thôi
    0.28
    éĤ£æĺ¯
    0.26
     Fantastic
    0.26
    _mr
    0.25
    OUNTER
    0.25
    éĤ£åĦ¿
    0.25
    èĢģèĻİ
    0.24
    è¿ĻéĩĮæĺ¯
    0.24
    uit
    0.24
    [section
    0.24
    Activations Density 11.210%

    No Known Activations