© 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. 39236
    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
    (tm
    -0.30
     bio
    -0.28
     tm
    -0.28
     Tra
    -0.28
     Bench
    -0.27
     K
    -0.27
     Ma
    -0.27
     Wan
    -0.27
     Bio
    -0.27
     Barn
    -0.27
    POSITIVE LOGITS
    rogram
    0.27
     initializer
    0.26
    pher
    0.26
     nigeria
    0.25
    ationToken
    0.25
    åħ³åĪĩ
    0.25
     ordinarily
    0.25
    nl
    0.25
    _written
    0.25
    ','');↵
    0.24
    Activations Density 30.124%

    No Known Activations

    This feature has no known activations.