© 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. 4364
    Prev
    Next
    INDEX
    Explanations

    physical fitness and body transformation

    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
    ä½ĵåĬĽ
    -0.09
    æĸŃè£Ĥ
    -0.09
    èĥĸ
    -0.08
    巨大
    -0.08
    å®ı
    -0.08
    巨大çļĦ
    -0.08
    ç«ĭåľº
    -0.08
    æĹºçĽĽ
    -0.08
     Grande
    -0.08
    å®ĮäºĨ
    -0.08
    POSITIVE LOGITS
    æīĵæŃ»
    0.11
    æĶ¶æķĽ
    0.10
    èĴ²
    0.09
    ä¸įæķ¢
    0.09
    ç»ĵæŀĦæĢ§
    0.09
    èĥŀ
    0.09
    为导åIJij
    0.09
    æĿ·
    0.09
    achten
    0.09
    æĪ¾
    0.09
    Activations Density 0.030%

    No Known Activations