© 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. 21663
    Prev
    Next
    INDEX
    Explanations

    joined by

    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
    ä»Ģä¹Īä¸ľè¥¿
    -0.11
    éĩįçĤ¹é¢ĨåŁŁ
    -0.10
    /tos
    -0.10
    çļĦèĦ¸
    -0.10
    ä¸ĩ家
    -0.10
    ä¸ĢèĦļ
    -0.09
    çķĢ
    -0.09
    æĶ¾è¿ĩ
    -0.09
    _ICON
    -0.09
    ãĥ¼ãĤº
    -0.09
    POSITIVE LOGITS
    4
    0.09
    ä¾Ĩèĩª
    0.09
    æĿ¥èĩª
    0.09
    5
    0.08
    åIJĮè¡Į
    0.08
    -sama
    0.08
    8
    0.08
    大åıij
    0.08
    3
    0.08
    anger
    0.08
    Activations Density 0.036%

    No Known Activations