© 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. 2891
    Prev
    Next
    INDEX
    Explanations

    place names

    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
    诸侯
    -0.09
    rome
    -0.08
    gens
    -0.08
    ç«Ļéķ¿
    -0.08
    ERING
    -0.08
    uzzi
    -0.08
    igu
    -0.08
    æĪijè§īå¾Ĺ
    -0.08
    -cancel
    -0.08
    æŁ¥çľĭæĽ´å¤ļ
    -0.08
    POSITIVE LOGITS
    isms
    0.11
    iveness
    0.10
    å´ĩé«ĺ
    0.10
    åĵĦ
    0.09
    èĢĥåľº
    0.09
    gether
    0.09
    /***/
    0.08
    naire
    0.08
    è°Ł
    0.08
    erno
    0.08
    Activations Density 0.006%

    No Known Activations