© 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. 37842
    Prev
    Next
    INDEX
    Explanations

    dynamic creative, add, Google Ads, Universal Analytics, leads

    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
    樵
    -0.10
    éĽĦ
    -0.10
    æijŀ
    -0.09
    ough
    -0.09
    EqualTo
    -0.09
    èĦĨå¼±
    -0.09
    讨论
    -0.08
    fäll
    -0.08
    ç»Ĭ
    -0.08
     Startup
    -0.08
    POSITIVE LOGITS
    ives
    0.09
    ä¸ĢåĪĻ
    0.09
    æĬķæĶ¾
    0.08
    remark
    0.08
    æ£
    0.08
    èİŀ
    0.08
    ä¸İä¸ŃåĽ½
    0.08
    秾
    0.07
     Leads
    0.07
    leads
    0.07
    Activations Density 0.118%

    No Known Activations