© 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. 60794
    Prev
    Next
    INDEX
    Explanations

    posting to

    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
    å°¾
    -0.11
    åĨ¬
    -0.08
    Alias
    -0.08
     dec
    -0.08
    路线
    -0.08
    å¯IJ
    -0.08
    磫
    -0.08
    æĪij没
    -0.08
     miss
    -0.08
    å¨ĩ
    -0.08
    POSITIVE LOGITS
    åħŃåIJĪ
    0.10
    è¾ĵ
    0.09
    ä¹¾åĿ¤
    0.09
    ä¸įç¦ģ
    0.09
    ils
    0.09
     sublicense
    0.09
    éŃĶ
    0.09
    èįļ
    0.09
    AsyncResult
    0.09
    à¹Ħล
    0.08
    Activations Density 0.045%

    No Known Activations