© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23999
    Prev
    Next
    INDEX
    Explanations

    possibility or future impact

    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
    çĴŁ
    -0.10
    èĤ¯å®ļ
    -0.10
    å¾Ģå¾Ģ
    -0.09
    èĤ¯å®ļæĺ¯
    -0.09
    imb
    -0.08
    jas
    -0.08
    éĻ¡
    -0.08
    èĤĦ
    -0.08
    å¾Ģå¾Ģä¼ļ
    -0.08
    è´¬
    -0.08
    POSITIVE LOGITS
    åľ¨æľªæĿ¥
    0.13
    å°ĨæĿ¥
    0.11
     someday
    0.10
    ä¸Ģ头
    0.10
     future
    0.10
    æĺİå¹´
    0.10
     Soon
    0.09
    æ©IJ
    0.09
    æľªæĿ¥
    0.09
    ä¸Ģè¾ĪåŃIJ
    0.09
    Activations Density 0.056%

    No Known Activations