© 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. 15682
    Prev
    Next
    INDEX
    Explanations

    quick thing

    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
     sometime
    -0.07
    åı¯åĸľ
    -0.07
    inc
    -0.07
    ä¼ļæľīä¸ĢäºĽ
    -0.07
    åı¯ä»¥çIJĨ解
    -0.07
    è¿Ļéĥ¨åĪĨ
    -0.06
    .innerHeight
    -0.06
    enson
    -0.06
    ayout
    -0.06
    ινÏĮ
    -0.06
    POSITIVE LOGITS
    å¿«åľ°
    0.09
     quick
    0.08
     schnell
    0.08
    è¿ħéĢŁåľ°
    0.08
    è¿ħéĢŁ
    0.08
     سرÛĮع
    0.08
    edList
    0.07
    æĺ¾
    0.07
     rej
    0.07
    brief
    0.07
    Activations Density 0.019%

    No Known Activations