© 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. 49061
    Prev
    Next
    INDEX
    Explanations

    patch, badges, stickers

    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
    elman
    -0.10
    æįĨ
    -0.09
    ä¸ĢéŨ
    -0.09
    ç¼ł
    -0.09
    弥漫
    -0.09
    .bundle
    -0.09
    èµ·åĪ°äºĨ
    -0.08
    ä¸Ģ楼
    -0.08
    æĭ¢
    -0.08
    第ä¸Ģä½į
    -0.08
    POSITIVE LOGITS
    è´´
    0.12
    è¿ĻåĿĹ
    0.11
    è²¼
    0.11
     plaque
    0.10
    ä¸Ģæŀļ
    0.10
     pla
    0.10
    éĿ¢ç§¯
    0.10
    æĸij
    0.10
    çĸ¤
    0.10
    ä¸ĢåĿĹ
    0.09
    Activations Density 0.086%

    No Known Activations