© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 62066
    Prev
    Next
    INDEX
    Explanations

    in comparison 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
    Not in Any Lists

    No Comments

    Negative Logits
    imax
    -0.09
    å¥Ĺ
    -0.09
    æīįæľī
    -0.09
    MAIL
    -0.09
    ä¿®æŃ£
    -0.09
    æ®Ĭ
    -0.08
    rian
    -0.08
    urar
    -0.08
    urons
    -0.08
    ä¸įåIJĮçļĦ
    -0.08
    POSITIVE LOGITS
    å°Ķæĸ¯
    0.10
    æīĵ好
    0.10
    åıijå±ķ空éĹ´
    0.09
    ä¹ŁæĹłæ³ķ
    0.09
    æ´ĹåĩĢ
    0.09
    åIJİæľŁ
    0.09
    æĪ¢
    0.09
    åĴĮæľįåĬ¡
    0.09
     transf
    0.09
     amount
    0.09
    Activations Density 0.157%

    No Known Activations