© 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. 55637
    Prev
    Next
    INDEX
    Explanations

    sporting or boasting

    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
    ONY
    -0.10
    è¨Ĺ
    -0.10
    ä»Ģä¹ĪæŶåĢĻ
    -0.09
    OrNull
    -0.09
    urst
    -0.09
    ryan
    -0.09
    亢
    -0.09
    éĢĤ
    -0.09
    å®ŀè´¨æĢ§
    -0.09
    ળ
    -0.08
    POSITIVE LOGITS
    ä¸Ģåī¯
    0.11
    çĿĢ
    0.10
    æĸ°æĬĢæľ¯
    0.10
    æĸ°çļĦ
    0.09
    pone
    0.09
    ä¸įåIJĮçļĦ
    0.09
    鬣
    0.09
    nez
    0.08
    ä¸Ģ身
    0.08
    èijŃ
    0.08
    Activations Density 0.009%

    No Known Activations