© 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. 38671
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    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
     datasets
    -0.28
     parameters
    -0.28
     outputs
    -0.28
    åıĤæķ°
    -0.27
     variables
    -0.27
     averages
    -0.26
    èĮ±
    -0.26
     résultats
    -0.26
     products
    -0.25
    (outputs
    -0.25
    POSITIVE LOGITS
     unconstitutional
    0.30
    âĢĹ
    0.29
     waive
    0.29
     waived
    0.28
    Authority
    0.28
    stick
    0.27
     Presidency
    0.27
    ominated
    0.27
     revoke
    0.27
     Funeral
    0.26
    Activations Density 17.130%

    No Known Activations