© 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. 7325
    Prev
    Next
    INDEX
    Explanations

    opportunities offered by

    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¸ĮæľĽèĥ½å¤Ł
    -0.10
    ÑĪив
    -0.08
    èĭĵ
    -0.08
    enthal
    -0.08
    å°ıé¢Ŀ贷款
    -0.08
    åĬłä»¥
    -0.08
     Stick
    -0.08
    èĭ¥æĤ¨
    -0.08
     Velvet
    -0.08
     Giov
    -0.08
    POSITIVE LOGITS
    æıIJä¾ĽçļĦ
    0.12
     offered
    0.11
     offerings
    0.11
    æīĢæıIJä¾Ľ
    0.10
    带æĿ¥çļĦ
    0.10
     доÑģÑĤÑĥп
    0.10
     disponibles
    0.09
    æľºä¼ļ
    0.09
    rong
    0.09
    ä¼ģä¸ļæıIJä¾Ľ
    0.09
    Activations Density 0.056%

    No Known Activations