© 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. 11374
    Prev
    Next
    INDEX
    Explanations

    in order to + verb

    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
    ÅĤÄħ
    -0.11
    occ
    -0.09
    ç®ĢçĽ´å°±æĺ¯
    -0.09
    çļĦå°±æĺ¯
    -0.09
    è¦ģæĺ¯
    -0.09
    åłŀ
    -0.09
    ä»¥äººä¸ºæľ¬
    -0.09
    幺
    -0.09
     ведÑĮ
    -0.09
    ä¹ŁæŃ£æĺ¯
    -0.09
    POSITIVE LOGITS
    æĽ´å¥½åľ°
    0.15
    è¾¾åĪ°
    0.11
    æĽ´å¥½çļĦ
    0.10
    ä¸į失
    0.10
    æĹ©æĹ¥
    0.09
    æĺİ天
    0.09
     better
    0.09
     tránh
    0.08
    æĽ´å¥½
    0.08
    èİ·å¾Ĺ
    0.08
    Activations Density 0.054%

    No Known Activations