© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37032
    Prev
    Next
    INDEX
    Explanations

    largely do

    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
    cul
    -0.09
    çĶŁäº§æĢ»
    -0.08
    wow
    -0.08
    inters
    -0.08
    æĻ®åıĬ
    -0.08
    ç»Ħç»ĩé¢Ĩ导
    -0.08
    ç»ĺ
    -0.08
    æĹłç©·
    -0.08
    enses
    -0.08
    çĶŁæ´»æ°´å¹³
    -0.07
    POSITIVE LOGITS
    追æį§
    0.11
    追éĢIJ
    0.11
    éĿĴçĿIJ
    0.11
    åIJ¸å¼ķåĬĽ
    0.10
    æĬ±åĽ¢
    0.10
     hấp
    0.10
    æĶ¶çĽĬçİĩ
    0.10
    æĬķè¡Į
    0.10
    æĹºçĽĽ
    0.10
    èĥĥåı£
    0.10
    Activations Density 0.067%

    No Known Activations