© 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. 11427
    Prev
    Next
    INDEX
    Explanations

    of the

    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
    çļĦä¸ĢäºĽ
    -0.10
    ä¸ĢåĪĩéĥ½
    -0.10
    äºĨä¸ĢäºĽ
    -0.10
    çļĦåIJĦ项
    -0.10
    çļĦåIJĦç§į
    -0.10
    äºĨå¾Īå¤ļ
    -0.10
    ä¸Ģæĸ¹éĿ¢
    -0.09
    ä¸ĢåĽ¢
    -0.09
    æĹ¶ä»£ä¸ŃåĽ½
    -0.09
    çļĦæľĢä½³
    -0.09
    POSITIVE LOGITS
    å±¥
    0.09
    inders
    0.09
    InnerText
    0.08
    çĶŁäº§çĶŁæ´»
    0.08
    ende
    0.08
    屯
    0.08
    计
    0.08
    磼
    0.08
    å¸ĮæľĽèĥ½å¤Ł
    0.07
    wend
    0.07
    Activations Density 0.090%

    No Known Activations