© 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. 62882
    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
    Not in Any Lists

    No Comments

    Negative Logits
    éĨª
    -0.29
    urf
    -0.27
     CNS
    -0.27
    á»Ļc
    -0.27
    æ±ĩ
    -0.26
    ä¸İåıijå±ķ
    -0.26
    lez
    -0.25
    UFF
    -0.25
    contres
    -0.25
    itu
    -0.24
    POSITIVE LOGITS
    ushman
    0.28
    abox
    0.26
    ç¼İ
    0.25
    æĪij们认为
    0.25
    -mort
    0.24
    Steam
    0.24
    ä¸ĵåijĺ
    0.24
    海滨
    0.24
    Ħ件
    0.23
    ![
    0.23
    Activations Density 2.461%

    No Known Activations

    This feature has no known activations.