© 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. 26835
    Prev
    Next
    INDEX
    Explanations

    past tense verbs and ownership/creation markers

    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
    ç»Ļ人ä¸Ģç§į
    -0.09
    ayah
    -0.08
    à²Ł
    -0.08
    åIJİæİĴ
    -0.08
    ystack
    -0.08
    FunctionFlags
    -0.08
    åħµåĽ¢
    -0.08
    lays
    -0.08
    fel
    -0.08
    åĨĽäºº
    -0.08
    POSITIVE LOGITS
    ç§įç§į
    0.09
    inder
    0.09
    è´
    0.08
    çļĦä¸ĢåĪĩ
    0.08
    ennen
    0.08
    天ä¸ĭ
    0.08
    åĴĮåľ°åĮº
    0.08
    çļĦä¸ľè¥¿
    0.08
    æ²£
    0.08
    ãĤĤãģ®ãģ¯
    0.08
    Activations Density 0.078%

    No Known Activations