© 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. 34208
    Prev
    Next
    INDEX
    Explanations

    processes ending in -tion / -ment

    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
    人们çļĦ
    -0.10
    ivre
    -0.10
    ÐľÐŀ
    -0.10
    andes
    -0.09
    åģļæ³ķ
    -0.09
    моÑĤ
    -0.09
    èĢģèĻİ
    -0.09
    .Restr
    -0.09
    geries
    -0.09
    çļĦåģļæ³ķ
    -0.09
    POSITIVE LOGITS
    åĴĮåıijå±ķ
    0.10
    ç¡Ģ
    0.09
    åĴĮå®ĮåĸĦ
    0.08
    é«ĺå±Ĥ次
    0.08
    婶
    0.08
    æĢĤ
    0.08
    没æľīæĥ³åĪ°
    0.08
    éĿ¢çĽ®
    0.08
    é«ĺè´¨éĩı
    0.07
    æĿŀ
    0.07
    Activations Density 0.332%

    No Known Activations