© 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. 38926
    Prev
    Next
    INDEX
    Explanations

    Copyright license or identifier

    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
    æĺ¯æĪijçļĦ
    -0.12
    --
    -0.10
    ا
    -0.09
    culate
    -0.09
    æĪ¢
    -0.08
    æĥ³ä¸įåĪ°
    -0.08
    zelf
    -0.08
    åľ¨ä»ĸçļĦ
    -0.08
    åľ¨æľªæĿ¥
    -0.08
    ãĥ³
    -0.08
    POSITIVE LOGITS
    =-=-=-=-=-=-=-=-
    0.12
    =-=-=-=-
    0.10
    âĢIJ
    0.10
     sẵ
    0.09
    Ñģкоп
    0.09
     Äijẹ
    0.09
    Ùij
    0.09
    ìį¨
    0.09
    ends
    0.09
    serv
    0.09
    Activations Density 0.496%

    No Known Activations