© 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. 25527
    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
    å¹³åĿĩæ°´å¹³
    -0.30
    idal
    -0.28
    éĿ¢ç§¯çº¦
    -0.28
    好ä¹ħ
    -0.27
     tasar
    -0.27
    upro
    -0.26
    angkan
    -0.26
     pinch
    -0.25
    é¼¾
    -0.25
    åıijå±ķ模å¼ı
    -0.25
    POSITIVE LOGITS
     Great
    0.31
    ?
    0.29
     Tri
    0.28
    Great
    0.28
     -
    0.28
    pent
    0.27
     Con
    0.27
     –
    0.27
    Âł
    0.27
     Day
    0.27
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.