© 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. 33-TRANSCODER-HP
    7. 52861
    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_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     relent
    -0.31
    管å±Ģ
    -0.27
    æł·
    -0.27
    ï¹į
    -0.26
     spared
    -0.26
     conspic
    -0.25
    è¿ľæĸ¹
    -0.25
    ${
    -0.25
    åį°èĬ±
    -0.24
    _stmt
    -0.24
    POSITIVE LOGITS
    ↵↵
    0.28
     !↵↵
    0.28
    :!
    0.27
     :
    0.27
     -:
    0.27
     It
    0.27
     ðŁĻĤ
    0.27
     :-
    0.26
    -↵↵
    0.26
     –
    0.26
    Activations Density 0.088%

    No Known Activations