© 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. 2017
    Prev
    Next
    INDEX
    Explanations

    died of or from

    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
    以èĩ³äºİ
    -0.09
    æķ´ä¸ªäºº
    -0.09
    é¾Ħ
    -0.09
     tháºŃm
    -0.08
    é¼İ
    -0.08
    arde
    -0.08
    _EXPR
    -0.08
    immer
    -0.08
    ä¸ĵåijĺ
    -0.08
    abor
    -0.08
    POSITIVE LOGITS
    讳
    0.11
    æŁIJç§į
    0.11
    ä»Ģä¹Īåij¢
    0.10
    ä»Ģä¹ĪåİŁåĽł
    0.10
    çļĦå°±æĺ¯
    0.09
    æĶ¹åıĺäºĨ
    0.09
    è¿ĻçĤ¹
    0.09
    çļĦä¸ľè¥¿
    0.09
    åIJĦæł·
    0.09
    åIJĦç§į
    0.08
    Activations Density 0.017%

    No Known Activations