© 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. 36538
    Prev
    Next
    INDEX
    Explanations

    Hello World

    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
    ç¼ł
    -0.09
    æŁ±
    -0.08
     cand
    -0.08
    è·Ĥ
    -0.08
    мел
    -0.08
    æĢ¨
    -0.08
    æ±ł
    -0.08
    窨
    -0.08
    ä¿®
    -0.08
    èįīæ¡Ī
    -0.08
    POSITIVE LOGITS
    oust
    0.09
    è¿ĻåĿĹ
    0.09
    èIJ½
    0.08
    åĩłåı¥
    0.08
    à¸Ľà¸£
    0.08
    _FALL
    0.08
     наÑģ
    0.08
     ìĿ´ê²ĥìĿĢ
    0.08
    nox
    0.08
    èĪ¬çļĦ
    0.08
    Activations Density 0.315%

    No Known Activations