© 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. 57232
    Prev
    Next
    INDEX
    Explanations

    cable systems, currency bank, meat balls

    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
    æıª
    -0.11
    ç»Ļä½łä»¬
    -0.10
    éĿĴæĺ¥æľŁ
    -0.10
    å¨ħ
    -0.10
    ören
    -0.10
    diet
    -0.09
    å¾®éĩıåħĥç´ł
    -0.09
    é¢Ĭ
    -0.09
    kul
    -0.09
    èĴ²
    -0.09
    POSITIVE LOGITS
    ç¡IJ
    0.09
    çļĦåĬ¨åĬĽ
    0.08
    èĦī
    0.08
    ãĥł
    0.08
    ENT
    0.08
    JOR
    0.07
    æĹ¥å¸¸å·¥ä½ľ
    0.07
    Hum
    0.07
     Literary
    0.07
    å°ıé¢Ŀ贷款
    0.07
    Activations Density 0.030%

    No Known Activations