© 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. 24-TRANSCODER-HP
    7. 149419
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    仪表
    -0.31
    mát
    -0.27
     warranted
    -0.26
    åľ¨åħ¶
    -0.25
    éŀŃ
    -0.25
    åĨ³è®®
    -0.24
    rium
    -0.24
    åĽ½éĻħæľºåľº
    -0.24
    è£ģå®ļ
    -0.23
    ,,,,,,,,
    -0.23
    POSITIVE LOGITS
    \Php
    0.27
    èĩªçĶ±
    0.26
    è¿ĻæĶ¯
    0.24
    .rad
    0.24
    alous
    0.24
    flate
    0.24
    ÄIJT
    0.24
    大大æıIJé«ĺ
    0.24
    HostException
    0.24
    è¿Ļå¥Ĺ
    0.24
    Activations Density 0.773%

    No Known Activations

    This feature has no known activations.