© 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. 26318
    Prev
    Next
    INDEX
    Explanations

    register to view

    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
    ITT
    -0.09
    æ±īåŃIJ
    -0.09
    aya
    -0.09
    kÅĤad
    -0.08
    allocated
    -0.08
     Gibson
    -0.08
    ule
    -0.08
    èģĶ缣
    -0.08
    çļĦ帮åĬ©
    -0.08
    è®´
    -0.08
    POSITIVE LOGITS
    èĻ¹
    0.10
    ç»ĵå®ŀ
    0.10
    èĢ³è¾¹
    0.10
    享æľī
    0.09
    éĩįä¸Ń
    0.09
    缼å¼Ģ
    0.09
    è¿ľæ´ĭ
    0.09
    çľĭçĤ¹
    0.09
    åĬ¨æĦŁ
    0.09
    缴è¾ĸ
    0.09
    Activations Density 0.019%

    No Known Activations