© 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. 35-TRANSCODER-HP
    7. 40774
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    urat
    -0.28
    atura
    -0.28
    天åłĤ
    -0.27
    "},"
    -0.26
    æĸĽ
    -0.26
    icz
    -0.25
     academy
    -0.24
    udit
    -0.24
    ",{
    -0.24
    orest
    -0.24
    POSITIVE LOGITS
    below
    0.29
    åģľä¸ĭæĿ¥
    0.28
    æ¡Įä¸Ĭ
    0.26
    çļĦä¸Ģ款
    0.25
    è¿ĺæľīä»Ģä¹Ī
    0.25
     employing
    0.25
    controlled
    0.24
    è·ª
    0.24
    ãģ§ãģĹãĤĩãģĨ
    0.24
    mont
    0.24
    Activations Density 16.211%

    No Known Activations

    This feature has no known activations.