© 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. 38534
    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
     (...
    -0.29
    ä¸įè¿ĩ
    -0.28
    oug
    -0.28
    ÑģÑĤÑĢаива
    -0.27
     disemb
    -0.26
    åIJĮæł·
    -0.26
     sparing
    -0.26
    oran
    -0.26
    æľ¬ä¹¦
    -0.26
     choked
    -0.25
    POSITIVE LOGITS
    forg
    0.29
    atrix
    0.27
    andard
    0.26
    .Matrix
    0.25
    hear
    0.25
    çľĭä¸Ģä¸ĭ
    0.24
    bam
    0.24
    bsolute
    0.24
    ingleton
    0.24
    Hyper
    0.24
    Activations Density 1.778%

    No Known Activations

    This feature has no known activations.