© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35600
    Prev
    Next
    INDEX
    Explanations

    courtesy of

    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
    å¤©çľŁ
    -0.10
    æű
    -0.10
     ÑĢа
    -0.10
    ä½łä¸į
    -0.09
    éºŁ
    -0.09
    æĸ¹å¼ıè¿Ľè¡Į
    -0.09
    Contours
    -0.09
     поÑĤÑĢебиÑĤел
    -0.09
    otre
    -0.09
    ât
    -0.09
    POSITIVE LOGITS
    æĺ¯æĪij
    0.12
    æĿ¥èĩªäºİ
    0.12
    æĿ¥èĩª
    0.11
     courtesy
    0.10
    ral
    0.10
    æĿ¥æºIJäºİ
    0.10
    cour
    0.10
    åĩºèĩª
    0.09
    æĭ¿äºĨ
    0.09
    å¾ĹçĽĬäºİ
    0.09
    Activations Density 0.068%

    No Known Activations