© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50774
    Prev
    Next
    INDEX
    Explanations

    St. Alban's Andrews Foundation

    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
     Stout
    -0.10
    zer
    -0.09
    ä¹ĭåĪĿ
    -0.09
    大èĥĨ
    -0.09
    oleon
    -0.08
    rocess
    -0.08
    æ½ĺ
    -0.08
    红
    -0.08
    åıijè¡Į
    -0.08
    ç²¾ç¥ŀçĹħ
    -0.08
    POSITIVE LOGITS
    aky
    0.10
    ä¸ĺ
    0.08
     PSA
    0.08
    天ä¸ĭ
    0.08
    è´¬
    0.08
    åħļé£İ
    0.08
    çīµ
    0.08
     REGARD
    0.08
    æ¯ķä¸ļåIJİ
    0.08
    ãģªãĤīãģªãģĦ
    0.08
    Activations Density 0.006%

    No Known Activations