© 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. 1056
    Prev
    Next
    INDEX
    Explanations

    tug-of-war, jugular, lugwardine

    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
     kinds
    -0.10
    гÑĢад
    -0.10
    ãģªãĤĬ
    -0.09
    -spe
    -0.09
    аÑĤоÑĢ
    -0.09
    izer
    -0.09
     ÑģÑĤилÑĮ
    -0.09
    -thinking
    -0.09
     Mey
    -0.09
     "('
    -0.09
    POSITIVE LOGITS
    lify
    0.10
    ä¸įä¸Ĭ
    0.10
    tur
    0.10
    æıĦ
    0.09
    ertext
    0.09
    ä¸į失
    0.09
    æ¶ķ
    0.09
    abyte
    0.09
    swith
    0.09
    æĬĹéľĩ
    0.09
    Activations Density 0.016%

    No Known Activations