© 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. 35760
    Prev
    Next
    INDEX
    Explanations

    lists of types or categories

    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
    azed
    -0.11
    zes
    -0.09
    澤
    -0.08
    éĦ¢
    -0.08
    ä¼ĺè¶Ĭ
    -0.08
    èıĸ
    -0.08
    å°ı康社ä¼ļ
    -0.08
    ClassName
    -0.08
    æĸĩåѸ
    -0.08
    æµģéĢļ
    -0.08
    POSITIVE LOGITS
    çī¹æ®ĬæĥħåĨµ
    0.14
    çī¹æ®Ĭ
    0.13
    è¿ĺæľīä¸ĢäºĽ
    0.13
    港澳
    0.13
     special
    0.11
    çī¹æ®ĬçļĦ
    0.11
    å¤ĸ交
    0.10
    å¼Ĥåľ°
    0.09
    çĶļèĩ³æĺ¯
    0.09
    åĽ½éĻħåIJĪä½ľ
    0.09
    Activations Density 0.267%

    No Known Activations