© 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. 23618
    Prev
    Next
    INDEX
    Explanations

    presence

    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
    ovie
    -0.11
    绣
    -0.10
    èļĬ
    -0.10
    åħ¥æīĭ
    -0.09
    éĤĪ
    -0.09
    weekly
    -0.09
    hek
    -0.09
     ÙħÙĨÙĩا
    -0.08
    ä¼Łå¤§
    -0.08
    ç¹ģ
    -0.08
    POSITIVE LOGITS
    éĻªåIJĮ
    0.13
    éĻªçĿĢ
    0.13
    åľ¨ä¸ĢæĹģ
    0.12
    éĻªä¼´
    0.11
    _present
    0.11
    åħ¨ç¨ĭ
    0.11
    Present
    0.11
     witnessing
    0.11
    éĻª
    0.11
     presente
    0.10
    Activations Density 0.046%

    No Known Activations