© 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. 63382
    Prev
    Next
    INDEX
    Explanations

    switching, features, irc, math, code

    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
    æĻ·
    -0.10
    лев
    -0.09
    ÑĢаÐ
    -0.09
    追
    -0.09
    /watch
    -0.09
    æľ
    -0.09
     Lawn
    -0.09
    ุม
    -0.09
    óm
    -0.08
    èĨ¨
    -0.08
    POSITIVE LOGITS
    åĬ©
    0.09
    å½ķéŁ³
    0.09
    åIJ¬åĬĽ
    0.09
    éªĮè¯ģçłģ
    0.09
    è¯Ŀ
    0.09
    æ·¡
    0.09
    éŁ³
    0.08
    éĢļè¯Ŀ
    0.08
    æ´ĭèij±
    0.08
    æİ¥åIJ¬
    0.08
    Activations Density 0.305%

    No Known Activations