© 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. 10364
    Prev
    Next
    INDEX
    Explanations

    possessive names

    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
    å¯Į
    -0.09
    æľį
    -0.09
    ital
    -0.09
    èĪĶ
    -0.08
    ADER
    -0.08
    çľ¼ç¥ŀ
    -0.08
    æŃ£å¸¸çļĦ
    -0.08
    èĤļåŃIJ
    -0.08
    æļijåģĩ
    -0.08
    éĴĵé±¼
    -0.08
    POSITIVE LOGITS
    ableView
    0.09
    å¦Ļ
    0.09
    IMS
    0.09
    è¿Ļ项
    0.08
    odia
    0.08
    FLT
    0.08
    æĤª
    0.08
    .Raise
    0.08
    abad
    0.08
    IEWS
    0.08
    Activations Density 0.066%

    No Known Activations