© 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. 40591
    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
    ailles
    -0.31
    rieved
    -0.26
    æ¬Ħ
    -0.24
    ographics
    -0.24
    auc
    -0.24
    )V
    -0.24
    åĴĮè°IJ
    -0.24
    tron
    -0.23
     outs
    -0.23
    adow
    -0.23
    POSITIVE LOGITS
    èıĢ
    0.28
     plagiar
    0.27
    heed
    0.26
    åĴĢ
    0.26
    exercise
    0.26
    éĽĨç»ĵ
    0.26
     manoe
    0.25
    ewis
    0.25
    åĩĢåľŁ
    0.25
    ä¸įåħĭ
    0.25
    Activations Density 3.881%

    No Known Activations

    This feature has no known activations.