© 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. 48596
    Prev
    Next
    INDEX
    Explanations

    paths, sake, Date, New, potential, ocean, brain, experimental

    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
    æ¡ĥ
    -0.09
    ronics
    -0.09
    ume
    -0.09
    åĨįä¹Łä¸į
    -0.08
    gar
    -0.08
    æ¾İæ¹ĥæĸ°éĹ»
    -0.08
    nable
    -0.08
    åĩºçĤī
    -0.08
    LEX
    -0.08
    är
    -0.08
    POSITIVE LOGITS
    æĸ¹éĿ¢çļĦ
    0.10
    追溯
    0.09
    ç²¹
    0.09
    å¹´çļĦ
    0.09
    \Bundle
    0.09
    éģµå®Ī
    0.08
    azo
    0.08
    åĪ«çļĦ
    0.08
    æĪ¿ä»·
    0.08
     aspects
    0.08
    Activations Density 0.233%

    No Known Activations