© 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. 32362
    Prev
    Next
    INDEX
    Explanations

    for those not familiar

    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
     GPLv
    -0.09
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.09
    æķ´é½IJ
    -0.09
    апÑĢ
    -0.09
    antis
    -0.09
    åºĻ
    -0.09
    éĬ®
    -0.08
     Bedford
    -0.08
    xiety
    -0.08
    éħįä¸Ĭ
    -0.08
    POSITIVE LOGITS
    è¿Ļæĺ¯ä¸Ģç§į
    0.13
    åIJ¬è¯´è¿ĩ
    0.12
    æĺ¯ä¸Ģç§į
    0.11
    ä¸įäºĨ解
    0.11
     obscure
    0.10
    æĺ¯ä¸Ģ家
    0.10
    çļĦæ¦Ĥ念
    0.09
    æĺ¯ä»Ģä¹Ī
    0.09
    åİī害
    0.09
    çļĦä¸Ģç§į
    0.09
    Activations Density 0.204%

    No Known Activations