© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52672
    Prev
    Next
    INDEX
    Explanations

    food safety

    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
    çŁ³èĨı
    -0.09
    éĻ¶
    -0.09
    æłijæŀĹ
    -0.08
    æļ´é£İ
    -0.08
    éĢłæŀĹ
    -0.08
    裸
    -0.08
    æ·¤
    -0.08
     книг
    -0.08
    éĿĴèĽĻ
    -0.08
    atar
    -0.08
    POSITIVE LOGITS
    让æ¶Īè´¹èĢħ
    0.13
    é£Łåĵģ
    0.13
    é£Łåĵģå®īåħ¨
    0.13
    é£İåij³
    0.11
    åĻ¨åħ·
    0.11
    æ¶Īè´¹èĢħ
    0.11
    æ¶Īè´¹èĢħçļĦ
    0.11
     food
    0.10
    é²ł
    0.10
    åĬłå·¥
    0.10
    Activations Density 0.417%

    No Known Activations