© 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. 37819
    Prev
    Next
    INDEX
    Explanations

    description of situation

    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
    æĪIJé¾Ļ
    -0.09
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    -0.09
    ç¼¢
    -0.09
     Bought
    -0.09
     Ult
    -0.08
    åį¡çīĩ
    -0.08
     Sunrise
    -0.08
    /reference
    -0.08
    åĸĦæĦı
    -0.08
    EventArgs
    -0.08
    POSITIVE LOGITS
    å¤Ħå¢ĥ
    0.11
    çļĦæĥħå½¢
    0.10
     situation
    0.10
    ç»Ŀ大éĥ¨åĪĨ
    0.10
    à¸łà¸²à¸§à¸°
    0.10
    çļĦæł·åŃIJ
    0.10
    çİ°çĬ¶
    0.10
    大éĥ¨åĪĨ
    0.10
    UFF
    0.10
    çļĦéĤ£ç§į
    0.10
    Activations Density 0.087%

    No Known Activations