© 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. 25426
    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
    ä¸įæŃ»
    -0.29
    éľĦ
    -0.26
    ç¥ŀä»Ļ
    -0.26
    .esp
    -0.26
    åİ»çľĭ
    -0.26
    æ¸İ
    -0.25
    符åı·
    -0.25
    åIJ¸å¼ķåĬĽ
    -0.25
    ait
    -0.25
     binder
    -0.24
    POSITIVE LOGITS
    ade
    0.29
    meg
    0.27
    ging
    0.25
    лаÑģ
    0.25
    ä¹ĭå¿ĥ
    0.24
    æ«
    0.24
    еж
    0.24
    rade
    0.24
    æľºåħ³
    0.24
    iesen
    0.24
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.