© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59190
    Prev
    Next
    INDEX
    Explanations

    differentiate or distinguish from

    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
    Negative Logits
     xuyên
    -0.10
    æŃª
    -0.09
    å±ķåĩº
    -0.09
    azzi
    -0.09
    arin
    -0.09
    mps
    -0.08
    æ¯ģ
    -0.08
    ä¸Ģèµ·åİ»
    -0.08
    ç´§æī£
    -0.08
    å½±
    -0.08
    POSITIVE LOGITS
    åĮºåĪ«
    0.16
    åĮºåĪĨ
    0.15
    iating
    0.11
    çļĦåĮºåĪ«
    0.10
    ters
    0.10
    åºıå¹ķ
    0.10
     distingu
    0.10
     ÑģÑĢеди
    0.10
    åĪĨåĮĸ
    0.10
     fark
    0.10
    Activations Density 0.060%

    No Known Activations