© 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. 25547
    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
     study
    -0.25
    ibbon
    -0.25
    study
    -0.25
    oday
    -0.25
    ization
    -0.25
    efa
    -0.24
    éĹ´éļĻ
    -0.24
    Haz
    -0.23
     ogl
    -0.23
    ledon
    -0.23
    POSITIVE LOGITS
    辩
    0.28
    åĥ¹åĢ¼
    0.26
    便äºİ
    0.26
    ä¸ºè¿Ľä¸ĢæŃ¥
    0.25
    ,:,:
    0.25
    clidean
    0.24
    .validator
    0.24
    çī¹æĿĥ
    0.24
     Vend
    0.24
    æĢ»ä»·
    0.24
    Activations Density 0.017%

    No Known Activations

    This feature has no known activations.