© 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. 20304
    Prev
    Next
    INDEX
    Explanations

    special offers and deals

    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
    ä¼Łå¤§çļĦ
    -0.09
    çķĶ
    -0.09
    该æĢİä¹Ī
    -0.08
    饱
    -0.08
    æ¸ħç®Ĺ
    -0.08
    饱满
    -0.08
    æįŀ
    -0.08
    lessly
    -0.08
    ument
    -0.08
    æ¸ħé¦Ļ
    -0.08
    POSITIVE LOGITS
    :len
    0.09
    æ¤ĭ
    0.09
    溲
    0.09
    orca
    0.09
    æĪ¢
    0.08
     ÐijÑĥд
    0.08
    第ä¸ĢåIJį
    0.08
    ÑģÑĤал
    0.08
    ADM
    0.08
    æ¯ĸ
    0.08
    Activations Density 0.003%

    No Known Activations