© 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. 53985
    Prev
    Next
    INDEX
    Explanations

    prevent disease

    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
    ewe
    -0.10
    æĬ¥åijĬæľŁåĨħ
    -0.09
    æĦį
    -0.09
    æ·ĩ
    -0.08
     scape
    -0.08
    æŸ
    -0.08
    éļĺ
    -0.08
    æĪijå°±
    -0.08
    å±ĢéĿ¢
    -0.08
     Gentle
    -0.08
    POSITIVE LOGITS
    intern
    0.10
    çĶ¨æ°´
    0.09
    éĹªçĶµ
    0.09
    çĺ«
    0.09
    讲究
    0.09
    æĽĿ
    0.08
    лав
    0.08
    å¹³åİŁ
    0.08
    enberg
    0.08
    adders
    0.08
    Activations Density 0.002%

    No Known Activations