© 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. 25244
    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
    Not in Any Lists

    No Comments

    Negative Logits
    SuccessListener
    -0.25
    (sender
    -0.25
    æ³³
    -0.25
     Cla
    -0.25
    Ä°R
    -0.24
    _RAW
    -0.24
     Wo
    -0.23
    overe
    -0.23
     swims
    -0.23
    sted
    -0.23
    POSITIVE LOGITS
    大åıij
    0.26
    è¾ĥéķ¿
    0.26
    inctions
    0.26
    跻身
    0.26
    å¼Ģåıij
    0.26
    åĨĽ
    0.26
    人群ä¸Ń
    0.26
    ocr
    0.25
    åİŁèijĹ
    0.25
    é«ĺæĸ°æĬĢæľ¯
    0.25
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.