© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20202
    Prev
    Next
    INDEX
    Explanations

    Japanese TV, Easter, Eddie Murphy

    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
    æĶ¾æīĭ
    -0.09
    elay
    -0.09
    лин
    -0.09
    é²ľæ´»
    -0.09
    çī¯
    -0.09
     needed
    -0.09
    setUp
    -0.09
    åĨ·éĿĻ
    -0.08
     cork
    -0.08
    强æľīåĬĽ
    -0.08
    POSITIVE LOGITS
    åĬ£
    0.13
    åªļ
    0.12
    éĤ£ç§į
    0.11
    ç«ĸ
    0.10
    æīĢè°ĵçļĦ
    0.10
    è¾ĥå·®
    0.09
    è±
    0.09
    è°Ħ
    0.09
    庸
    0.09
    éĤ£æł·çļĦ
    0.09
    Activations Density 0.208%

    No Known Activations