© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51272
    Prev
    Next
    INDEX
    Explanations

    possessive 's

    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
    ä¸ĸçķĮçļĦ
    -0.10
    æīĭ表
    -0.09
    æīĭä¸Ĭ
    -0.09
     Millenn
    -0.08
    _dash
    -0.08
    esco
    -0.08
     ног
    -0.08
    andle
    -0.08
     Fet
    -0.08
    ÑĮ
    -0.08
    POSITIVE LOGITS
    æŶå°ļ
    0.10
    红åĪ©
    0.10
    ç§įç§į
    0.09
    åįİ侨
    0.09
    诱æĥij
    0.09
    积æŀģä½ľçĶ¨
    0.08
    lef
    0.08
    çļĦæĥħæĦŁ
    0.08
    CTION
    0.08
    oter
    0.08
    Activations Density 0.071%

    No Known Activations