© 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. 39881
    Prev
    Next
    INDEX
    Explanations

    doi identifiers

    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
    oter
    -0.11
    æĺ¯è¦ģ
    -0.08
    羯
    -0.08
    ç´ł
    -0.08
    å¹£
    -0.08
     hesitant
    -0.08
    ç»Ĩèħ»
    -0.08
    éĿ¢çĽ®
    -0.08
    tle
    -0.08
    rish
    -0.08
    POSITIVE LOGITS
    æĬĢæľ¯æľįåĬ¡
    0.09
     Sunder
    0.09
    jej
    0.09
    饿
    0.09
    æĦŁåºĶ
    0.09
    踪
    0.09
    æİ©
    0.09
    .EventHandler
    0.08
    lov
    0.08
    è¡Ķ
    0.08
    Activations Density 0.033%

    No Known Activations