© 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. 10342
    Prev
    Next
    INDEX
    Explanations

    time progression

    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
     оÑģобенно
    -0.10
    _indexes
    -0.10
    è¿Ļæīį
    -0.10
    æŃ£åĢ¼
    -0.09
    ä¸ĢçĽ´ä»¥æĿ¥
    -0.09
    è¿ijå¹´æĿ¥
    -0.09
    æѤæŶ
    -0.09
    秣
    -0.08
    æŃ¤æ¬¡
    -0.08
    _don
    -0.08
    POSITIVE LOGITS
    å°±æľīäºĨ
    0.10
    å°±æĪIJäºĨ
    0.09
    åĨįå¤ļ
    0.09
    æĪij们就
    0.09
    æĪIJ为ä¸ŃåĽ½
    0.09
    æĪIJåŀĭ
    0.09
    å°±èĥ½
    0.09
    åĨĴåĩº
    0.09
    ä¸įè§ģäºĨ
    0.09
    å¼Ģå§ĭäºĨ
    0.09
    Activations Density 0.034%

    No Known Activations