© 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. 40510
    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
    vvm
    -0.30
    çĶµä»·
    -0.27
    ä¸ĩ象
    -0.25
    {}",
    -0.25
     spokes
    -0.25
    olar
    -0.25
    ä¸ĩåħĥ以ä¸Ĭ
    -0.25
    Mate
    -0.25
    pla
    -0.24
     Replies
    -0.24
    POSITIVE LOGITS
    earned
    0.27
     pools
    0.27
     Hobby
    0.26
    lie
    0.26
    å§Ķæīĺ
    0.25
    -dr
    0.24
    ctors
    0.24
    asic
    0.24
    并éĢļè¿ĩ
    0.24
    移交
    0.24
    Activations Density 76.009%

    No Known Activations

    This feature has no known activations.