© 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. 38728
    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
    oji
    -0.10
    ÑģÑĤо
    -0.09
    åĩ¡æĺ¯
    -0.09
    inth
    -0.09
    å¬ī
    -0.09
    åij±
    -0.09
    æĢĥ
    -0.08
    รส
    -0.08
    辩è¯ģ
    -0.08
    @student
    -0.08
    POSITIVE LOGITS
    ãĤĩãģĨ
    0.09
    åĨľä¸ļç§ijæĬĢ
    0.09
    ä»ĭ
    0.09
    å·¥ä½ľæľºåĪ¶
    0.09
    0.08
    æĿ²
    0.08
    enance
    0.08
    ãĤ¢ãĥĥãĥĹ
    0.08
    æŀĩ
    0.08
    ä¸ĬãģĴ
    0.08
    Activations Density 0.032%

    No Known Activations