© 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. 29609
    Prev
    Next
    INDEX
    Explanations

    wines, Japan, Tennessee State, first harvest, first recipient, first scenario

    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
    çİĭåĽ½
    -0.09
     crochet
    -0.08
    å·©
    -0.08
    说æĪij
    -0.08
    æ°ij主
    -0.08
    ÑģÑĤолÑĮ
    -0.08
    ç«ĻçĿĢ
    -0.08
    ç§ijæķĻ
    -0.07
    æīĢ以æĪij
    -0.07
    æħ
    -0.07
    POSITIVE LOGITS
    产åĮº
    0.12
    clone
    0.10
    åįķåĵģ
    0.10
    éħ¿éħĴ
    0.09
    ç¼
    0.09
    говоÑĢ
    0.09
    (clone
    0.09
     clones
    0.09
    çļĦ表çİ°
    0.09
    æī¹éĩı
    0.09
    Activations Density 0.031%

    No Known Activations