© 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. 40723
    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
    SP
    -0.26
     Dise
    -0.26
    ancies
    -0.25
    ãĢĤwww
    -0.25
    ç»ĵ
    -0.25
    lik
    -0.25
     kappa
    -0.25
     kicker
    -0.24
    /utility
    -0.23
    [ID
    -0.23
    POSITIVE LOGITS
    imet
    0.30
    -font
    0.26
    伸
    0.25
     graphs
    0.25
     Orlando
    0.25
    men
    0.24
    éĢĢ
    0.24
    ILED
    0.24
    BH
    0.24
    ffe
    0.24
    Activations Density 80.785%

    No Known Activations

    This feature has no known activations.