© 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. 12371
    Prev
    Next
    INDEX
    Explanations

    what questions / digit questions

    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
    榷
    -0.10
    æĪijè¿ĺæĺ¯
    -0.10
    æĸ¹æĸ¹éĿ¢éĿ¢
    -0.09
    çĩİ
    -0.09
     же
    -0.09
    åIJĦæĸ¹
    -0.09
    èĥ½ä¸įèĥ½
    -0.09
    æ¬Ħ
    -0.09
    çݺ
    -0.09
    ç¾ģ
    -0.09
    POSITIVE LOGITS
    eci
    0.09
    ýt
    0.08
    à¸Ħะ
    0.08
    amat
    0.07
    æīĵãģ¡
    0.07
     Sle
    0.07
     Wong
    0.07
    عÙĦا
    0.07
    ube
    0.07
    å®ĺ
    0.07
    Activations Density 0.263%

    No Known Activations