© 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. 57326
    Prev
    Next
    INDEX
    Explanations

    eating habits or diet

    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
    å°ıèħ¿
    -0.10
    çºłéĶĻ
    -0.09
    éħ±
    -0.09
    æŀ§
    -0.09
    å§ĭ
    -0.09
    é¢Ĩ
    -0.09
    æĮ¤
    -0.08
    ounces
    -0.08
    çŁ¢
    -0.08
    æµ´
    -0.08
    POSITIVE LOGITS
    é¥Ńèıľ
    0.13
    å¿«é¤IJ
    0.12
    é£Łçī©
    0.10
    é£
    0.09
     fare
    0.09
    飯
    0.09
    _spin
    0.09
    æĹ©é¤IJ
    0.09
    åIJŀ
    0.09
    饱
    0.09
    Activations Density 0.067%

    No Known Activations