© 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. 7212
    Prev
    Next
    INDEX
    Explanations

    Spintronics, Cape Breton, Villains, Axact, National Alliance

    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
     endregion
    -0.10
    çļĦå¿ĥçIJĨ
    -0.08
    bbing
    -0.08
    累累
    -0.08
     enumerate
    -0.08
    @qq
    -0.07
    å¿ĥçIJĨ
    -0.07
    åīľ
    -0.07
    pek
    -0.07
    çļĦ游æĪı
    -0.07
    POSITIVE LOGITS
    ä»Ģä¹Īåij¢
    0.10
    æīĢè°ĵçļĦ
    0.09
    çIJı
    0.09
     пÑĢоÑģÑĤо
    0.09
    æ¯Ķå¦Ĥ说
    0.09
    èĬ±äºĨ
    0.09
    åįłæį®äºĨ
    0.08
    æģ°å½ĵ
    0.08
    èĪªè¿IJ
    0.08
    帽
    0.08
    Activations Density 0.602%

    No Known Activations