© 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. 60768
    Prev
    Next
    INDEX
    Explanations

    legible, recognizable, intelligible

    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
    éĻª
    -0.11
    æĤ¬æµ®
    -0.09
    æī¿
    -0.08
    笼
    -0.08
    utta
    -0.08
    åĴĮå°ļ
    -0.08
     Wrong
    -0.08
    iku
    -0.08
    èijĽ
    -0.08
    好å¥ĩ
    -0.08
    POSITIVE LOGITS
    çľĭä¸įåĩº
    0.14
    éĿ¢çĽ®
    0.13
    éĿ¢è²Į
    0.12
    辨
    0.12
     recognizable
    0.11
    çľĭä¸įè§ģ
    0.11
    认
    0.11
    èªį
    0.10
    è¯ĨåĪ«
    0.10
     пÑĢоÑģ
    0.10
    Activations Density 0.146%

    No Known Activations