© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 48540
    Prev
    Next
    INDEX
    Explanations

    Osborne

    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
     гаÑĢ
    -0.10
     ë¶Ī구íķĺê³ł
    -0.10
    æĪĸå¤ļ
    -0.09
    æĪijçİ°åľ¨
    -0.09
    è¡®
    -0.09
    缨
    -0.08
    涩
    -0.08
    åĽ¾å½¢
    -0.08
    æĻŀ
    -0.08
    ä¹°åįķ
    -0.08
    POSITIVE LOGITS
    aiser
    0.10
    otch
    0.09
    icum
    0.09
    æĹ¥æĻļ
    0.09
    erving
    0.09
    attern
    0.08
    yster
    0.08
    éļ§
    0.08
    ÙĦ
    0.08
    ITU
    0.08
    Activations Density 0.002%

    No Known Activations