© 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. 47672
    Prev
    Next
    INDEX
    Explanations

    excretion and removal

    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
    æĬķæĶ¾
    -0.10
    æĶ¾å¤§
    -0.10
    好åIJĥ
    -0.10
    æ¹ĥ
    -0.09
    æ°°
    -0.09
    游åĩ»
    -0.09
    äºĭæķħåıijçĶŁ
    -0.09
    æ¾
    -0.09
    åij³
    -0.09
    æŀģ大çļĦ
    -0.09
    POSITIVE LOGITS
    åĩºåİ»
    0.14
    带走
    0.14
    æİĴåĩº
    0.11
    à¸Ńà¸Ńà¸ģมา
    0.10
    ä¸Ģéĥ¨åĪĨ
    0.09
     via
    0.09
    à¸Ńà¸Ńà¸ģà¹Ħà¸Ľ
    0.08
    åĩºè·¯
    0.08
    æİĴéĻ¤
    0.08
     untranslated
    0.08
    Activations Density 0.161%

    No Known Activations