© 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. 59314
    Prev
    Next
    INDEX
    Explanations

    volleyball and medical incontinence terms

    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
    åħij
    -0.11
    åį±å®³
    -0.10
    AIT
    -0.10
    åĬ±
    -0.10
    BITS
    -0.09
    åĵ¥ä»¬
    -0.09
    åĤĴ
    -0.09
    ãģªãģı
    -0.09
    trak
    -0.09
    æ·±è¿ľ
    -0.09
    POSITIVE LOGITS
    女æİĴ
    0.11
     volleyball
    0.10
    iable
    0.09
    uro
    0.09
    ä½ľåĩº
    0.09
    æ°¸è¿ľä¸įä¼ļ
    0.09
    olum
    0.08
    åij¨è½¬
    0.08
     Legion
    0.08
    Marvel
    0.08
    Activations Density 0.143%

    No Known Activations