© 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. 11392
    Prev
    Next
    INDEX
    Explanations

    sensitization and hypersensitivity

    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
    åĶ®ç¥¨
    -0.09
    æİ©çĽĸ
    -0.09
    quis
    -0.09
    æ²Ł
    -0.09
    èµĭäºĪ
    -0.08
    çĨ¬
    -0.08
    åĽ½å®¶æĪĺçķ¥
    -0.08
     ÑĢеÑĪа
    -0.08
    åĴª
    -0.08
    éĶ»çĤ¼
    -0.08
    POSITIVE LOGITS
    æ¯ģ
    0.10
    éģ¨
    0.09
    æīĵäºĨ
    0.09
    主管
    0.09
    èµ°åľ¨
    0.09
    æīĵ
    0.09
    踩
    0.09
    ilst
    0.09
    ario
    0.09
    ÑĢак
    0.08
    Activations Density 0.414%

    No Known Activations