© 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. 39174
    Prev
    Next
    INDEX
    Explanations

    emergency calls and alerts

    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
    ZE
    -0.10
    éŀĺ
    -0.09
    æİ¥å¾ħ
    -0.09
    æݨå¼Ģ
    -0.08
    å¿Ļç¢Į
    -0.08
    çī©ç§į
    -0.08
    æĺ¨æĹ¥
    -0.08
    æŀ¶åŃIJ
    -0.08
    鹿
    -0.08
    满æĦı
    -0.08
    POSITIVE LOGITS
    åĩĨç¡®æĢ§
    0.12
    éĢĥçĶŁ
    0.10
    误ä¼ļ
    0.09
    æĬķèµĦé¢Ŀ
    0.09
    ä¸įä½İäºİ
    0.09
    ä¹İ
    0.09
    èĩªæķij
    0.09
    éķ¬
    0.09
    æ¯ħåĬĽ
    0.09
    è¾ľè´Ł
    0.09
    Activations Density 0.078%

    No Known Activations