© 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. 27764
    Prev
    Next
    INDEX
    Explanations

    polo, derby, heptathlon

    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
    etter
    -0.09
    ä¸įèµ·
    -0.09
    ference
    -0.08
    å§Ĭ妹
    -0.08
    åIJĮæł·çļĦ
    -0.08
    oral
    -0.08
    lessness
    -0.08
    lessly
    -0.08
    جاز
    -0.08
    lies
    -0.07
    POSITIVE LOGITS
    lio
    0.10
    ensis
    0.10
    uede
    0.09
    обоÑĢоÑĤ
    0.09
    æĮĩçĿĢ
    0.09
    shire
    0.09
    çļĦ人éĥ½
    0.09
    é»į
    0.09
    ÑĤай
    0.09
    ONES
    0.08
    Activations Density 0.002%

    No Known Activations