© 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. 50375
    Prev
    Next
    INDEX
    Explanations

    reported by news organizations

    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
    empo
    -0.10
    å¾Īå¤ļ人
    -0.10
     ourselves
    -0.09
    å¾Īå¤ļ人éĥ½
    -0.09
     Ñģами
    -0.09
    许å¤ļ人
    -0.09
    nl
    -0.09
    uParam
    -0.09
    éĻIJ
    -0.09
    æ¯ı个人
    -0.09
    POSITIVE LOGITS
     himself
    0.13
    åĴĮä»ĸçļĦ
    0.12
    (s
    0.10
    群ä½ĵ
    0.10
    åħ¶æīĢ
    0.10
    DataContext
    0.09
    ä»ĸçŁ¥éģĵ
    0.09
    ä»ĸçļĦ
    0.09
    ä»ĸèĩªå·±
    0.09
    åIJįåı«
    0.09
    Activations Density 0.352%

    No Known Activations