© 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. 62879
    Prev
    Next
    INDEX
    Explanations

    chili and chile related words

    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
    ly
    -0.09
    ê·¹
    -0.08
    æ®·
    -0.08
    ãĤ¼
    -0.08
    una
    -0.08
     sic
    -0.08
    pus
    -0.08
    paces
    -0.08
    ãģĵãģ¨ãģ§
    -0.08
    ually
    -0.08
    POSITIVE LOGITS
    æ»Ł
    0.09
    è·³åĩº
    0.09
    éŃĶ鬼
    0.09
    brook
    0.09
    uku
    0.09
    æģ¤
    0.09
    bear
    0.09
     ÑĤомÑĥ
    0.09
    éĽĨåĽ¢èĤ¡ä»½
    0.09
    æľī害
    0.08
    Activations Density 0.002%

    No Known Activations