© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26496
    Prev
    Next
    INDEX
    Explanations

    print, presentation, web, DOCUMENT, FILE

    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
    isses
    -0.09
    orta
    -0.09
     fabs
    -0.08
    è¯Ĭ
    -0.08
    okie
    -0.08
    çĸij
    -0.08
    fabs
    -0.08
    éļ¾
    -0.08
     bek
    -0.08
    æĶ¶åıĹ
    -0.08
    POSITIVE LOGITS
    ä¸įå®Į
    0.10
    å±ĬæŶ
    0.10
     Bow
    0.10
    ä¸ºçĽ®çļĦ
    0.09
     bow
    0.09
    ç»Ī究
    0.09
    æķĻèĤ²æķĻåѦ
    0.09
    ä¹Łå¥½
    0.09
    课åłĤæķĻåѦ
    0.09
     purposes
    0.09
    Activations Density 0.112%

    No Known Activations