© 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. 31951
    Prev
    Next
    INDEX
    Explanations

    weekend

    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
    ApplicationContext
    -0.09
    ç»ķ
    -0.08
    AME
    -0.08
    atan
    -0.08
     bull
    -0.08
    æĹ©æĻļ
    -0.08
    ame
    -0.07
    åİ»æİī
    -0.07
    å¼
    -0.07
    æĶ¯éĥ¨
    -0.07
    POSITIVE LOGITS
    çĭİ
    0.09
    enor
    0.09
    æĸĩ娱
    0.09
     Ùħباشرة
    0.09
    没äºĨ
    0.09
    æĢĿç´¢
    0.09
    /board
    0.09
    ç¬ĶèĢħ
    0.09
    ä¼°
    0.08
    æģIJé¾Ļ
    0.08
    Activations Density 0.013%

    No Known Activations