© 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. 3097
    Prev
    Next
    INDEX
    Explanations

    shop or shopping for items

    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
    éĿ¢éĥ¨
    -0.09
    ãĤ§
    -0.09
    meld
    -0.08
    èĦ¸éĥ¨
    -0.08
    ech
    -0.08
     pres
    -0.08
    pres
    -0.08
    æľīç§į
    -0.08
    born
    -0.08
    иÑĩно
    -0.08
    POSITIVE LOGITS
    pping
    0.10
    çĽ¹
    0.10
    ä¸įä¿¡
    0.10
    ä¼ļåIJĮ
    0.09
    çĭIJ
    0.09
    åĶĨ
    0.09
    æľ¬æľŁ
    0.09
    课é¢ĺ
    0.09
    åĴĮæĬĢæľ¯
    0.09
    åºķä¸ĭ
    0.09
    Activations Density 0.025%

    No Known Activations