© 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. 16927
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by a word

    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
    æĽ´æĺ¯
    -0.10
    å¤ķ
    -0.09
    èĪĢ
    -0.09
    åĪ¹
    -0.08
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.08
    楸
    -0.08
    èĥĮåIJİçļĦ
    -0.08
    åºķå±Ĥ
    -0.08
    çī¹æĸ¯
    -0.08
    大家åı¯ä»¥
    -0.08
    POSITIVE LOGITS
    å¿ĻçĿĢ
    0.09
    èĥ½ä½¿
    0.09
    inen
    0.08
     disap
    0.08
    èĩªç§°
    0.08
    æľī个
    0.08
    æĪĸ许æĺ¯
    0.08
    éĴ¤
    0.08
     lazy
    0.08
    交ç»ĩ
    0.08
    Activations Density 0.997%

    No Known Activations