© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52238
    Prev
    Next
    INDEX
    Explanations

    data privacy and protection

    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
     зак
    -0.08
    çĸı
    -0.08
    anova
    -0.08
    æ²ı
    -0.08
    æĹ¥æĻļéĹ´
    -0.08
     Milo
    -0.08
     delivering
    -0.08
    æ³
    -0.08
    èĦļ
    -0.08
    ä»Ģä¹Īéĥ½
    -0.08
    POSITIVE LOGITS
     GDPR
    0.12
    个人信æģ¯
    0.11
    è·¨å¢ĥ
    0.10
    éļIJç§ģ
    0.10
     Privacy
    0.10
    åĨ²æ´Ĺ
    0.10
    èij¡èIJĦçīĻ
    0.10
     privacy
    0.09
    rights
    0.09
     rights
    0.09
    Activations Density 0.057%

    No Known Activations