© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29517
    Prev
    Next
    INDEX
    Explanations

    select, -only, wise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÙĪØ·
    -0.09
    Assignable
    -0.08
    affer
    -0.08
    agar
    -0.07
    çķª
    -0.07
    ĵĺ
    -0.07
    åħ¨èĪ¬
    -0.07
    åıĬéħį件
    -0.07
    affen
    -0.07
    mani
    -0.07
    POSITIVE LOGITS
    âĦ¢
    0.08
    æĺ¯ä»Ģä¹ĪæĦıæĢĿ
    0.08
    æķĪåºĶ
    0.08
    çݰ象
    0.07
    ä¹ĭ称çļĦ
    0.07
    ãģ¨åij¼ãģ°ãĤĮãĤĭ
    0.07
     czyli
    0.07
    æĺ¯æĮĩ
    0.07
    æĮĩçļĦæĺ¯
    0.07
    åįİéĺ³
    0.07
    Activations Density 0.395%

    No Known Activations