© 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. 23-TRANSCODER-HP
    7. 23361
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    erspective
    -0.29
    èį¯
    -0.27
    åĩºæ¼Ķ
    -0.25
    èĩĨ
    -0.24
    ãĤĨ
    -0.24
    è®©ä½ł
    -0.24
    æľīå¾Īå¤ļç§į
    -0.24
    éªĿ
    -0.24
    è¿Ļç§įæĸ¹å¼ı
    -0.24
    çł´
    -0.24
    POSITIVE LOGITS
     vol
    0.29
    wich
    0.26
     bÃłn
    0.26
    arking
    0.24
    \↵
    0.24
    urement
    0.24
    ework
    0.24
     repay
    0.24
     Still
    0.23
    nation
    0.23
    Activations Density 0.018%

    No Known Activations

    This feature has no known activations.