© 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. 56498
    Prev
    Next
    INDEX
    Explanations

    tracking, detective, clues, leads

    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
    æģIJ
    -0.09
    æĭ¥æĬ±
    -0.09
    å¯¹æľªæĿ¥
    -0.09
    示
    -0.09
    彩
    -0.09
     示
    -0.08
     здоÑĢов
    -0.08
    .newInstance
    -0.08
    示èĮĥ
    -0.08
    æħ¨
    -0.08
    POSITIVE LOGITS
    线索
    0.22
    追踪
    0.18
    åıĸè¯ģ
    0.15
    溯æºIJ
    0.14
    侦æİ¢
    0.14
    è¯ģæį®
    0.14
    èĽĽ
    0.13
    踪
    0.13
    è·Łè¸ª
    0.13
     clues
    0.13
    Activations Density 0.062%

    No Known Activations