© 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. 60635
    Prev
    Next
    INDEX
    Explanations

    expected or projected future events

    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
    羣çļĦæĺ¯
    -0.11
    泯
    -0.09
    éĥ½ä¸įæĺ¯
    -0.09
    è¿Ļæĺ¯æĪij
    -0.09
    éļ¾åıĹ
    -0.08
    头çĸ¼
    -0.08
    红æĺŁ
    -0.08
    容
    -0.08
    è¿ĩ大
    -0.08
     lem
    -0.08
    POSITIVE LOGITS
    æľŁæľĽ
    0.25
     expected
    0.23
    é¢ĦæľŁ
    0.23
    é¢Ħ计
    0.20
     expect
    0.20
    expected
    0.20
    Expected
    0.18
    æľŁå¾ħ
    0.18
    _EXPECT
    0.18
    _expected
    0.18
    Activations Density 0.138%

    No Known Activations