© 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. 38910
    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
    Not in Any Lists

    No Comments

    Negative Logits
    :disable
    -0.30
     diapers
    -0.25
     somehow
    -0.25
     glyphicon
    -0.24
    itals
    -0.24
    rine
    -0.23
    kontakte
    -0.23
    aned
    -0.23
    ridden
    -0.23
     unavoidable
    -0.23
    POSITIVE LOGITS
    ĥģ
    0.31
    éķ¿çŁŃ
    0.29
     Plan
    0.29
     plan
    0.29
    æ³³
    0.28
     laid
    0.28
    Plan
    0.26
    /A
    0.26
    æĪijæĥ³
    0.26
    plan
    0.25
    Activations Density 1.797%

    No Known Activations

    This feature has no known activations.