© 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. 38749
    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
    ietf
    -0.28
    èĩ¼
    -0.26
    itness
    -0.25
    çģı
    -0.25
    iams
    -0.24
    /*----------------------------------------------------------------
    -0.23
    .findAll
    -0.23
    ìĦ¤
    -0.23
    riding
    -0.23
    éĿ¢çĽ®
    -0.22
    POSITIVE LOGITS
    mania
    0.26
    ember
    0.25
     åķ
    0.25
    coder
    0.25
    æľĿçĿĢ
    0.24
    ä¸Ńæ¯Ĵ
    0.24
    isper
    0.24
    å¨ľ
    0.24
     chù
    0.23
    大åݦ
    0.23
    Activations Density 0.034%

    No Known Activations

    This feature has no known activations.