© 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. 11485
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with division

    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
    大éĥ¨åĪĨ
    -0.08
    ä¸įåĬ¨
    -0.08
     Midwest
    -0.08
    .pickle
    -0.08
    çīĻ
    -0.08
    redd
    -0.08
     бил
    -0.08
     chiff
    -0.08
    åѦèĢħ
    -0.08
     Cust
    -0.07
    POSITIVE LOGITS
    é¡·
    0.10
    è¯Ł
    0.10
    èĢĢçľ¼
    0.10
    ä¸Ģ头
    0.10
    IgnoreCase
    0.10
    éĵ¨
    0.09
    æľīåħ³è§Ħå®ļ
    0.09
    åı¹æģ¯
    0.09
    è¶Ł
    0.09
    åĽ«
    0.09
    Activations Density 0.191%

    No Known Activations