© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 54220
    Prev
    Next
    INDEX
    Explanations

    people roles

    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
    æĪij们éĥ½
    -0.11
    对çĿĢ
    -0.10
    æĪij以为
    -0.10
    ä»»
    -0.10
    ä»İä¸ļ
    -0.10
    æĪij们就
    -0.10
    æĪij们ä¼ļ
    -0.10
    ä½łå°±
    -0.09
    TA
    -0.09
    ãģĮãĤī
    -0.09
    POSITIVE LOGITS
     Karn
    0.10
    亢
    0.09
    çļĦä¸ĢåĪĩ
    0.09
    å·²æľī
    0.08
    -parent
    0.08
    幸
    0.08
    çļĦä¸ĢéĿ¢
    0.08
    çļĦä¸Ģç§į
    0.08
    -kind
    0.08
    çļĦåIJĮæŶ
    0.08
    Activations Density 0.364%

    No Known Activations