© 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. 142571
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ials
    -0.33
     Claud
    -0.24
    Own
    -0.23
    æĭ¥
    -0.23
    Paren
    -0.23
    acy
    -0.23
    uter
    -0.23
     Hi
    -0.22
    éĴŁ
    -0.22
    olley
    -0.22
    POSITIVE LOGITS
    åľ°åĿª
    0.24
     suk
    0.23
    产ä¸ļåŁºåľ°
    0.23
    emens
    0.23
     Triá»ģu
    0.22
    visualization
    0.22
    æ´»è·ĥ
    0.22
    æĹłæķ°æ¬¡
    0.22
    åľºæĻ¯
    0.22
    unks
    0.22
    Activations Density 26.257%

    No Known Activations

    This feature has no known activations.