© 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. 63909
    Prev
    Next
    INDEX
    Explanations

    no followed by other words

    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
    ä¸įå½±åĵį
    -0.11
    æѤ类
    -0.10
    çļĦä¸ĢéĿ¢
    -0.09
    åįĬæľĪ
    -0.08
    ej
    -0.08
    çļĦæĦŁåıĹ
    -0.08
    neck
    -0.08
    regular
    -0.08
     regular
    -0.07
    åIJİæľŁ
    -0.07
    POSITIVE LOGITS
    说æĺ¯
    0.11
    ç¾½
    0.10
    嶷
    0.10
    说å¾Ĺ
    0.09
    裨
    0.09
     اÙĦÙĪÙĤ
    0.09
    é¡»
    0.09
    æĬĬå®ĥ
    0.09
    æĬĬ她
    0.09
    æķ·
    0.09
    Activations Density 0.014%

    No Known Activations