© 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. 40298
    Prev
    Next
    INDEX
    Explanations

    it was discovered

    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
    åĸ»
    -0.09
    åºŁ
    -0.09
    æĪijæĬĬ
    -0.09
    éĤ¯
    -0.09
     Ñģлова
    -0.08
    ãģ¨ãģĦãģĨãģ®ãģ¯
    -0.08
    uss
    -0.08
    çģŃ
    -0.08
    æŁ¬
    -0.08
    æĪij们ä¸Ģèµ·
    -0.08
    POSITIVE LOGITS
    äºĨ解åĪ°
    0.13
    认为
    0.12
    åıijè§ī
    0.12
    å¾ĹçŁ¥
    0.11
    åĨ³å®ļ
    0.11
    æ·±çŁ¥
    0.10
    认è¯ĨåĪ°
    0.10
    è¡·
    0.10
    注æĦıåĪ°
    0.10
    å¾Īæ¸ħæ¥ļ
    0.10
    Activations Density 0.110%

    No Known Activations