© 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. 26294
    Prev
    Next
    INDEX
    Explanations

    automobile, public, Riley, wearer, audience, patients, dog

    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
    çļĦç¡®
    -0.09
    èĭķ
    -0.09
    è°ľ
    -0.09
    éĹ®ä»ĸ
    -0.09
    çļĦ人æĿ¥è¯´
    -0.09
    ,to
    -0.09
    代价
    -0.08
    åĪ¶è®¢
    -0.08
    讫
    -0.08
    èĬľ
    -0.08
    POSITIVE LOGITS
    åħ³äºİ
    0.11
    åħį
    0.11
    innen
    0.09
    使åħ¶
    0.09
     Falling
    0.08
    جاÙħع
    0.08
     Lev
    0.08
    æŃ£å½ĵ
    0.08
    æİĴ
    0.08
    èĩ³äºİ
    0.08
    Activations Density 0.305%

    No Known Activations