© 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. 26943
    Prev
    Next
    INDEX
    Explanations

    cannot explain

    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
    æ¯Ĵ
    -0.09
    ander
    -0.09
    æĹ¢çĦ¶
    -0.09
    导
    -0.09
    avi
    -0.09
    ä¼ĺ
    -0.09
    Locator
    -0.09
     Grove
    -0.08
    \Object
    -0.08
    CPP
    -0.08
    POSITIVE LOGITS
    ä¸įæ¸ħ
    0.14
    ä¸įæ¸ħæ¥ļ
    0.13
    æĹłæķ°
    0.12
    说ä¸įåĩº
    0.12
     countless
    0.11
    太å¤ļäºĨ
    0.11
    ä¸įå®Į
    0.11
    ä¸į说
    0.11
    æĹłæ³ķ
    0.10
    æīĵäºĨ
    0.10
    Activations Density 0.061%

    No Known Activations