© 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. 30408
    Prev
    Next
    INDEX
    Explanations

    its origin, own, roots, moments, allure, way, utility

    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
     its
    -0.11
    å®ĥçļĦ
    -0.10
    åħ¶
    -0.10
    æIJŀ好
    -0.10
    ä»ĸä»¬åľ¨
    -0.09
    æ³ķå®Ŀ
    -0.09
    rô
    -0.09
    åľ¨åħ¶
    -0.09
    ament
    -0.08
    audi
    -0.08
    POSITIVE LOGITS
     Martins
    0.09
    ä¸Ģç«Ļ
    0.08
    ì¹ĺ
    0.08
    对åŃ©åŃIJ
    0.08
    ä¸Ģå¥Ĺ
    0.08
    ç³»
    0.08
    èĽ®
    0.08
    对éĿ¢
    0.08
    é¢ĦåijĬ
    0.08
    bound
    0.08
    Activations Density 0.040%

    No Known Activations