© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 31107
    Prev
    Next
    INDEX
    Explanations

    Japanese names / surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Greenwood
    -0.10
    çİĭåħĪçĶŁ
    -0.09
    æĪijçĽ¸ä¿¡
    -0.08
    æĹ©åľ¨
    -0.08
    opl
    -0.08
    axes
    -0.08
    ä¸įä»ħä»ħ
    -0.08
    æł¹æľ¬ä¸į
    -0.08
    é¦ĸåħĪæĺ¯
    -0.08
    å®Įåħ¨åı¯ä»¥
    -0.08
    POSITIVE LOGITS
    çŀŃ
    0.09
    åĪĨè¡Į
    0.09
    éĩĬ
    0.08
     eds
    0.08
    æµħ
    0.08
    è¯Ĩ
    0.08
    %C
    0.08
    ÙĨاس
    0.08
    å®ħ
    0.08
    ãĦ±
    0.08
    Activations Density 0.208%

    No Known Activations