© 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. 151381
    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
     sustained
    -0.27
    èµ°å»Ĭ
    -0.26
    verty
    -0.26
    kiego
    -0.25
    burgh
    -0.24
    æ´»ä¸ĭåİ»
    -0.23
    urse
    -0.23
     withdrawals
    -0.23
     national
    -0.23
    æݥ管
    -0.23
    POSITIVE LOGITS
    è¯Ńæ³ķ
    0.27
     Essence
    0.24
    _TERM
    0.23
     Costco
    0.23
    hamster
    0.23
    ä¼ļ被
    0.23
    ogui
    0.22
    odate
    0.22
     Ebony
    0.22
     Busy
    0.22
    Activations Density 0.124%

    No Known Activations

    This feature has no known activations.