© 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. 62426
    Prev
    Next
    INDEX
    Explanations

    body mass index

    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
    åľ¨æĪijåĽ½
    -0.09
    åĵķ
    -0.09
    强çĥĪ
    -0.09
    à¹Ģห
    -0.09
    è¾ĸ
    -0.08
    skip
    -0.08
    ä¸ĢæĹ¥
    -0.08
    avana
    -0.08
    æ¯ı天
    -0.08
     minus
    -0.08
    POSITIVE LOGITS
    èĥĸ
    0.12
     overweight
    0.10
     веÑģ
    0.10
    веÑģ
    0.09
    ä½ĵåŀĭ
    0.09
    riages
    0.09
     obesity
    0.09
    èѦ
    0.09
    ä¸Ģ缴éĥ½æĺ¯
    0.09
    BMI
    0.09
    Activations Density 0.129%

    No Known Activations