© 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. 1321
    Prev
    Next
    INDEX
    Explanations

    this <followed by explanation/example>

    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
    èĪ«
    -0.10
    槲
    -0.10
    ä¹ĭ举
    -0.09
    åįĬæľĪ
    -0.09
    æľªæĪIJ
    -0.09
    èĢĮä¸Ķè¿ĺ
    -0.09
    çļĦéĤ£ç§į
    -0.09
    æłĩçļĦ
    -0.09
    yro
    -0.09
     tagged
    -0.09
    POSITIVE LOGITS
     particular
    0.09
     Tir
    0.09
    æĺ¯æĮĩ
    0.08
     Ñģпин
    0.08
    è¿ĽæĿ¥
    0.08
    zap
    0.08
    æĺ¯æľĢ好çļĦ
    0.08
    лин
    0.08
    æĺİçıł
    0.08
    IOR
    0.08
    Activations Density 0.169%

    No Known Activations