© 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. 25403
    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
    å¿ĹæĦ¿
    -0.29
    æ½į
    -0.25
    elize
    -0.25
     Consum
    -0.25
    Void
    -0.24
     consumption
    -0.24
     Wer
    -0.24
     ****************************************************************************
    -0.24
    	wp
    -0.24
    \Route
    -0.23
    POSITIVE LOGITS
    å£
    0.27
    é³Į
    0.25
    illard
    0.25
    illos
    0.25
    èĩĤ
    0.24
    ê¸Ģ
    0.24
    åĿĽ
    0.24
     centrally
    0.24
    éĴĿ
    0.24
    зам
    0.24
    Activations Density 0.014%

    No Known Activations

    This feature has no known activations.