© 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. 60907
    Prev
    Next
    INDEX
    Explanations

    work their way through

    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
     Trot
    -0.10
    èħ¿éĥ¨
    -0.09
    inator
    -0.09
    å¼ĤæĢ§
    -0.09
    ä½İ温
    -0.09
    æĬķè¯ī
    -0.09
    éĿ´
    -0.09
    è¿Ī
    -0.09
    ä¹IJ
    -0.08
    å¢ĥ
    -0.08
    POSITIVE LOGITS
    æħ¢æħ¢
    0.10
    æħ¢æħ¢åľ°
    0.09
    æ¸IJæ¸IJ
    0.09
    çĻ¾å¼º
    0.09
    æħ¢æħ¢çļĦ
    0.09
    æ¼Ķ
    0.08
    éĢIJæ¸IJ
    0.08
    çī¹
    0.08
     slowly
    0.08
    ddl
    0.08
    Activations Density 0.046%

    No Known Activations