© 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. 942
    Prev
    Next
    INDEX
    Explanations

    respectively corresponding items

    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
    нÑĥÑģ
    -0.09
    ä¾ĿçĦ¶åŃĺåľ¨
    -0.08
     itself
    -0.08
    sait
    -0.07
    缴æİ¥æĬĬ
    -0.07
    ä¹ĭä¸Ģå°±æĺ¯
    -0.07
    åĽ¢åijĺ
    -0.07
    ä¸Ģèµ·åģļ
    -0.07
    å§ĭç»Ī以
    -0.07
    leger
    -0.07
    POSITIVE LOGITS
     respectively
    0.11
    åIJĦèĩª
    0.10
    åĪĨåĪ«
    0.10
    åIJĦæľī
    0.10
    åIJĦèĩªçļĦ
    0.10
    ãģĿãĤĮãģŀãĤĮ
    0.08
     respectiv
    0.08
    åĪĨåĪ¥
    0.08
    ä¸įåIJĮç¨ĭ度çļĦ
    0.08
    åIJĦ
    0.07
    Activations Density 0.045%

    No Known Activations