© 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. 8237
    Prev
    Next
    INDEX
    Explanations

    first-person statements or feelings

    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
    hart
    -0.08
    ãģ¯ãĤĤãģ¡ãĤįãĤĵ
    -0.08
    nd
    -0.08
    æĸĩæĺĮ
    -0.08
    marsh
    -0.08
    常å§Ķ
    -0.07
    çļĦ巨大
    -0.07
    ãģ«æĪ
    -0.07
    ãģĽãģļ
    -0.07
    ÑĢаж
    -0.07
    POSITIVE LOGITS
    æīĢåľ¨çļĦ
    0.10
    çļĦå¿ĥ
    0.10
    =-=-=-=-=-=-=-=-
    0.10
    ableObject
    0.09
    ease
    0.09
    ç»Ļ大家
    0.09
    .za
    0.09
    åĩºèº«
    0.09
     Sheikh
    0.09
    æ§İ
    0.09
    Activations Density 0.185%

    No Known Activations