© 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. 12227
    Prev
    Next
    INDEX
    Explanations

    free throw

    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
    æ¹Ľ
    -0.09
    awn
    -0.09
    ContextHolder
    -0.09
    곡
    -0.09
    äºĶæĺŁ
    -0.09
    åŁİéķĩ
    -0.09
    _NR
    -0.09
    ltra
    -0.09
    å¹ķ
    -0.08
    Fn
    -0.08
    POSITIVE LOGITS
    è¹Ń
    0.09
    æīĭèĦļ
    0.08
     fre
    0.08
    åIJİç»Ń
    0.08
    ç½ļ
    0.08
    /prom
    0.08
    çļĦä¸Ģ大
    0.08
    èµĦæľ¬
    0.08
    亲
    0.08
     lob
    0.08
    Activations Density 0.035%

    No Known Activations