© 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. 26213
    Prev
    Next
    INDEX
    Explanations

    expand or expand*

    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
    Negative Logits
    çķĻè¨ĢæĿ¿
    -0.10
    éĹ³
    -0.09
    ลà¸ļ
    -0.09
    空æ°Ķ
    -0.09
    trl
    -0.09
    åĭ¤å¥ĭ
    -0.09
    æĶ¹èī¯
    -0.09
    ä¼ļ产çĶŁ
    -0.08
    posit
    -0.08
    騰
    -0.08
    POSITIVE LOGITS
    èĮĥåĽ´
    0.14
     scope
    0.11
    åºĶçĶ¨åľºæĻ¯
    0.10
     ÙĨطاÙĤ
    0.10
    åIJĪä½ľåħ³ç³»
    0.10
    è§Ĩéĩİ
    0.10
    è¦ĨçĽĸéĿ¢
    0.09
    (scope
    0.09
    ä¹ĭå¤ĸ
    0.09
    ç¯Ħ
    0.09
    Activations Density 0.066%

    No Known Activations