© 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. 59064
    Prev
    Next
    INDEX
    Explanations

    Royal organizations

    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
    Not in Any Lists

    No Comments

    Negative Logits
    гла
    -0.10
    _zones
    -0.10
    äº
    -0.10
    æ°ijèĪª
    -0.09
     cogn
    -0.09
    å¦Ī
    -0.09
    åıijå±ķçļĦ
    -0.08
    æľįä»İ
    -0.08
    ModelIndex
    -0.08
    StackSize
    -0.08
    POSITIVE LOGITS
    éī´
    0.12
    å½ĵä¹ĭæĹłæĦ§
    0.10
    åĨįæĿ¥
    0.09
    ÙħØ´
    0.09
    strain
    0.09
    èİħ
    0.08
    éĢģå¾Ģ
    0.08
     Rah
    0.08
     strain
    0.07
    æĸ¹åı¯
    0.07
    Activations Density 0.113%

    No Known Activations