© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7550
    Prev
    Next
    INDEX
    Explanations

    smoking

    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
    æ¼ı
    -0.10
    bill
    -0.09
    鹤
    -0.08
    Ñģан
    -0.08
    è¿ĺä¸įæĺ¯
    -0.08
    éķĿ
    -0.08
    æİĴåĪĹ
    -0.08
    ORY
    -0.08
    çħ§æĺİ
    -0.08
    sher
    -0.08
    POSITIVE LOGITS
     repr
    0.10
    ä¸įå½ĵ
    0.09
    ä»»ä½ķå½¢å¼ı
    0.09
    ä¸įæŃ¢
    0.08
    ä¼ļ使
    0.08
    åľ¨æľªæĿ¥
    0.08
    å¦ĤæľŁ
    0.08
    idge
    0.08
    iegel
    0.08
    ä¼ļå½±åĵį
    0.08
    Activations Density 0.174%

    No Known Activations