© 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. 31-TRANSCODER-HP
    7. 17933
    Prev
    Next
    INDEX
    Explanations

    from

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     at
    -0.37
    æľ¬èº«
    -0.32
    å¿«
    -0.31
    initial
    -0.29
     fast
    -0.28
    Ut
    -0.28
     first
    -0.27
    æľ¬èº«çļĦ
    -0.27
    fast
    -0.27
    At
    -0.26
    POSITIVE LOGITS
     day
    0.41
    ä»İ
    0.37
    Day
    0.35
     Day
    0.34
    ä½Ĩä»İ
    0.34
    -day
    0.33
    	from
    0.33
     from
    0.32
    ä»İä¸Ń
    0.32
    _day
    0.31
    Activations Density 0.112%

    No Known Activations