© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 39453
    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
     final
    -0.35
     internal
    -0.34
     t
    -0.33
     up
    -0.33
     external
    -0.33
     arc
    -0.32
     ten
    -0.31
     "
    -0.30
     rapid
    -0.30
     feed
    -0.29
    POSITIVE LOGITS
     isempty
    0.30
     roma
    0.29
    isempty
    0.28
    kü
    0.27
    ately
    0.27
     predecess
    0.25
     uom
    0.25
    LETE
    0.25
    shade
    0.24
    uum
    0.24
    Activations Density 12.183%

    No Known Activations

    This feature has no known activations.