© 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. 4199
    Prev
    Next
    INDEX
    Explanations

    where to see

    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
    è´ª
    -0.10
    èĩªä¸»åĪĽæĸ°
    -0.09
    Subview
    -0.09
     Madd
    -0.09
    ä¸ĢåĽŀäºĭ
    -0.08
    è¿ĩåĪĨ
    -0.08
    ä¸Ģäºĭ
    -0.08
     bapt
    -0.08
    åıĤä¸İ
    -0.08
    éĦł
    -0.08
    POSITIVE LOGITS
    éĻ¨
    0.09
    èݽ
    0.09
    dl
    0.09
     NSError
    0.08
    ern
    0.08
    æĮ¥åıij
    0.08
    çļĦæĪIJ绩
    0.08
    weise
    0.08
    é«ĺ强度
    0.08
    holders
    0.08
    Activations Density 0.001%

    No Known Activations