© 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. 52915
    Prev
    Next
    INDEX
    Explanations

    free software

    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
    \\\
    -0.08
    åı¦å¤ĸ
    -0.08
    æĹ¶ä»£ä¸ŃåĽ½
    -0.07
    ductor
    -0.07
    å¼ģ
    -0.07
    -0.07
     ante
    -0.07
    ine
    -0.07
    å°±æĪIJäºĨ
    -0.07
    ended
    -0.07
    POSITIVE LOGITS
    çīĪæĿĥæīĢæľī
    0.10
    åľ»
    0.10
    请大家
    0.10
    请æĤ¨
    0.10
    天æ°Ķ
    0.09
    /tos
    0.09
     اÙĦÙħصدر
    0.09
    åı¹äºĨåı£æ°Ķ
    0.09
    ä¸įèī¯ä¿¡æģ¯
    0.09
    æĦŁåĨĴ
    0.09
    Activations Density 0.066%

    No Known Activations