© 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. 56084
    Prev
    Next
    INDEX
    Explanations

    Hong Kong

    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
    ted
    -0.10
    angan
    -0.09
    ials
    -0.09
    æģĤ
    -0.09
    ingle
    -0.09
    вл
    -0.09
    èĮ¸
    -0.09
    ments
    -0.09
    outh
    -0.09
    kiem
    -0.09
    POSITIVE LOGITS
    æ¹¾
    0.12
    ular
    0.10
    itory
    0.09
    emm
    0.09
    caps
    0.09
    versation
    0.09
    sdale
    0.08
    éĿ¢è²Į
    0.08
    ooks
    0.08
    quist
    0.08
    Activations Density 0.006%

    No Known Activations