© 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. 3576
    Prev
    Next
    INDEX
    Explanations

    ingredients and food items

    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
    inary
    -0.10
    éļ¾å¾Ĺ
    -0.10
    审æī¹
    -0.09
    ä¾¦æŁ¥
    -0.09
    審
    -0.09
    è¿Ľåº¦
    -0.09
    å°ijä¸įäºĨ
    -0.09
     sunrise
    -0.09
    ç¾Ĭæ¯Ľ
    -0.09
    ç²¾çĽĬæ±Ĥç²¾
    -0.09
    POSITIVE LOGITS
    çĸ½
    0.09
    çݳ
    0.09
    ette
    0.09
    ettes
    0.08
    -dominated
    0.08
    æĬĬè¿Ļ个
    0.07
    less
    0.07
    fty
    0.07
     Whit
    0.07
    İĺìĿ´
    0.07
    Activations Density 0.001%

    No Known Activations