© 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. 12095
    Prev
    Next
    INDEX
    Explanations

    positive qualities

    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
    ç»Ĩç»Ĩ
    -0.09
     so
    -0.09
    oron
    -0.09
    bubble
    -0.09
    ationToken
    -0.08
    åıij表äºĨ
    -0.08
    ayne
    -0.08
    è¿Ŀæ³ķçĬ¯ç½ª
    -0.08
    为ä¹ĭ
    -0.08
    az
    -0.08
    POSITIVE LOGITS
    æĦŁ
    0.11
    çļĦåIJĮæŶ
    0.10
    æĽ´å®¹æĺĵ
    0.09
    à¹ģละà¸Ħวาม
    0.08
    åĴĮåıijå±ķ
    0.08
    áĥ¢
    0.08
     Mess
    0.08
     ëįĶìļ±
    0.08
    å¥łå®ļ
    0.08
    èĤł
    0.08
    Activations Density 0.169%

    No Known Activations