© 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. 24351
    Prev
    Next
    INDEX
    Explanations

    I think I

    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
    ç»į
    -0.10
    è·ĭ
    -0.09
    éĢļ
    -0.09
    éŀŃ
    -0.09
    大éħĴåºĹ
    -0.08
    ä¹ĥ
    -0.08
    ä¸įç¡®å®ļ
    -0.08
    è¾ĩ
    -0.08
    åĪĨæĺİ
    -0.08
     лиÑĩно
    -0.08
    POSITIVE LOGITS
    èĬĹ
    0.09
    éªĮæĶ¶
    0.08
    ÑĩÑĥвÑģÑĤв
    0.08
    åħ±åIJĮä½ĵ
    0.08
     altogether
    0.08
     Lust
    0.08
    æĺİçĻ½äºĨ
    0.08
    èµŀ
    0.08
    locker
    0.08
    رÙĨ
    0.08
    Activations Density 0.041%

    No Known Activations