© 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. 39109
    Prev
    Next
    INDEX
    Explanations

    firefighter, power, privacy

    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
    åī©ä¸ĭçļĦ
    -0.08
    мел
    -0.08
    ks
    -0.08
    è¿Ļ个éĹ®é¢ĺ
    -0.08
    3
    -0.08
     пÑĢид
    -0.08
    积èĵĦ
    -0.08
     impossible
    -0.08
     Rodrig
    -0.08
    outer
    -0.07
    POSITIVE LOGITS
    éļIJç§ģ
    0.12
    ä¸įåĪ©äºİ
    0.11
    æīĢæıIJä¾Ľ
    0.11
    åį±éĻ©
    0.11
    æľªç»ı
    0.11
    æľªç»ıæİĪæĿĥ
    0.10
    privacy
    0.10
    æĶ¶è´¹
    0.10
    æľīæ¯Ĵ
    0.10
    çļĦç¾İ好
    0.10
    Activations Density 0.661%

    No Known Activations