© 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. 20224
    Prev
    Next
    INDEX
    Explanations

    all followed by a noun

    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
    ç»ĻæĤ¨
    -0.09
    è¶Ĭ
    -0.09
    å°Ĩåħ¶
    -0.09
    æĢ»ä¼ļ
    -0.09
    atat
    -0.09
    å°±è¶Ĭ
    -0.09
    èµĺ
    -0.08
    çļĦæķ´ä½ĵ
    -0.08
    BOOT
    -0.08
    .sg
    -0.08
    POSITIVE LOGITS
    第ä¸ī个
    0.10
    æĹ©æĻļ
    0.09
    å¾ģæĶ¶
    0.09
    æĥħå¢ĥ
    0.09
    bane
    0.09
    æĥħåĨµä¸ĭ
    0.08
    Void
    0.08
    ä¸įåĩº
    0.08
    ium
    0.08
    两èĢħ
    0.08
    Activations Density 0.038%

    No Known Activations