© 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. 38398
    Prev
    Next
    INDEX
    Explanations

    order dismissed granted denied

    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
    èµİ
    -0.09
    rex
    -0.09
    æ¯įæł¡
    -0.09
    æľĪèĸª
    -0.09
     ÑĥвеÑĢен
    -0.09
    .tm
    -0.09
    æĥ©æĪĴ
    -0.09
    åįķ纯çļĦ
    -0.09
    天èµĭ
    -0.09
     Hanna
    -0.09
    POSITIVE LOGITS
    æıIJåĩºçļĦ
    0.09
    é»İæĺİ
    0.08
    æIJŀ
    0.08
    趣
    0.08
    çĤĴèĤ¡
    0.08
    ç¥Ńç¥Ģ
    0.08
    æ¶Ī
    0.08
    nga
    0.08
     practise
    0.07
    éĺ´è°ĭ
    0.07
    Activations Density 0.140%

    No Known Activations