© 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. 8279
    Prev
    Next
    INDEX
    Explanations

    STEM education and careers

    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
    itag
    -0.11
    纵
    -0.09
    è¿ĽéŨ
    -0.09
    ä¸įåĪ°ä½į
    -0.09
    æĥij
    -0.09
    /license
    -0.09
    ä¸ĭçıŃ
    -0.09
    æĻ¨
    -0.09
    åĻ©
    -0.09
    éĹº
    -0.09
    POSITIVE LOGITS
    åIJİå¤ĩ
    0.09
    acus
    0.09
    é¢ĨåŁŁçļĦ
    0.08
    ieri
    0.08
    çIJīçĴĥ
    0.08
     gir
    0.08
    çķĮçļĦ
    0.08
    arsers
    0.08
     imagePath
    0.07
     lá»±c
    0.07
    Activations Density 0.014%

    No Known Activations