© 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. 64004
    Prev
    Next
    INDEX
    Explanations

    Lisp programming language constructs

    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
    _Framework
    -0.10
     Hawk
    -0.09
     обла
    -0.09
     Huff
    -0.09
    è½½ä½ĵ
    -0.09
     Alta
    -0.09
    å¼ĤæĢ§
    -0.09
    åķ¡
    -0.08
    éĿ¡
    -0.08
    _mappings
    -0.08
    POSITIVE LOGITS
    éĢ¸
    0.12
    anse
    0.10
    æĶ¶æĶ¯
    0.10
     Appe
    0.09
    æ·±åĮĸæĶ¹éĿ©
    0.09
    Unicode
    0.09
    èĩªçIJĨ
    0.09
    _unicode
    0.08
    æļ®
    0.08
    çŃĶ
    0.08
    Activations Density 0.111%

    No Known Activations