© 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. 1618
    Prev
    Next
    INDEX
    Explanations

    names of people

    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»ĨåĪĻ
    -0.10
    Jets
    -0.10
    edReader
    -0.09
    ç¥IJ
    -0.09
     lle
    -0.09
    azzi
    -0.08
    åľ¨ä»ĸ
    -0.08
    åĨ³èĥľ
    -0.08
    åľ¨è¿Ļç§į
    -0.08
     bust
    -0.08
    POSITIVE LOGITS
    鬯
    0.10
    åIJŀ
    0.09
    éĽĨåĽ¢èĤ¡ä»½
    0.09
    人身
    0.09
    å±±åºĦ
    0.09
    æIJľç´¢å¼ķæĵİ
    0.09
    åī¥ç¦»
    0.08
    .toBe
    0.08
    _defaults
    0.08
    éĹ©
    0.08
    Activations Density 0.002%

    No Known Activations