© 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. 38827
    Prev
    Next
    INDEX
    Explanations

    talk about

    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
    诤
    -0.09
    çĥĪ
    -0.09
    erring
    -0.08
    为äºĨæĽ´å¥½
    -0.08
    aires
    -0.08
    ackers
    -0.08
    主åĬ¨
    -0.08
    ëŁ¼
    -0.08
     Soviets
    -0.08
    chas
    -0.08
    POSITIVE LOGITS
    åIJĦèĩªçļĦ
    0.11
    åħ¶æīĢ
    0.11
    è¿Ļ件
    0.11
    ä»Ģä¹Īåij¢
    0.10
    urre
    0.10
    ç§įç§į
    0.10
    æѤäºĭ
    0.09
    è¿Ļ款
    0.09
    ä»ĸ对
    0.09
     Eh
    0.09
    Activations Density 0.192%

    No Known Activations