© 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. 40584
    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
     presentations
    -0.29
    eson
    -0.29
    æ³Ľ
    -0.28
     hom
    -0.28
     Hom
    -0.27
    .Expressions
    -0.26
    presentation
    -0.26
     Ext
    -0.26
     Military
    -0.25
    夸
    -0.25
    POSITIVE LOGITS
    ä»Ģ
    0.29
    rolling
    0.29
    nı
    0.28
    Merit
    0.27
    xious
    0.27
    å¤ĸåľ°
    0.27
     screenWidth
    0.26
    æī£
    0.26
    ache
    0.26
    宽
    0.26
    Activations Density 1.148%

    No Known Activations

    This feature has no known activations.