© 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. 27908
    Prev
    Next
    INDEX
    Explanations

    being, going, doing, making, moving, having

    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
     Kỳ
    -0.11
    åĨī
    -0.10
    平常
    -0.10
    izo
    -0.09
    èĴ¿
    -0.09
    æĸ¯é¡¿
    -0.09
    ston
    -0.09
    åį³å°ĨåĪ°æĿ¥
    -0.09
    æѤæŶ
    -0.09
    ä»»ä½ķæŶåĢĻ
    -0.09
    POSITIVE LOGITS
    éĿŀ常å¤ļçļĦ
    0.11
    ä¸įå°ij
    0.10
     quite
    0.10
    è¶ĬæĿ¥è¶Ĭ
    0.09
    è¶ĬæĿ¥
    0.09
    è¶ĬæĿ¥è¶Ĭå¤ļ
    0.09
    ém
    0.09
     lifetime
    0.09
    éĿŀ常å¤ļ
    0.09
    符åı·
    0.08
    Activations Density 0.025%

    No Known Activations