© 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. 18158
    Prev
    Next
    INDEX
    Explanations

    exam and assessment preparation

    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
    ablish
    -0.07
     Chess
    -0.07
    ouses
    -0.07
    ηγ
    -0.07
    tdown
    -0.07
    æŃī
    -0.07
    å¼Ģ课
    -0.07
     Artis
    -0.07
    å·¥ç¨ĭå¸ĪæĭĽèģĺ
    -0.07
    åľ¨ç¾İ
    -0.07
    POSITIVE LOGITS
    çŁ¥å·±
    0.09
    対çŃĸ
    0.08
    é«ĺåĪĨ
    0.08
     preparation
    0.08
    æĬĢå·§åĴĮ
    0.08
    åĨ³èĥľ
    0.08
     Preparation
    0.07
    åºĶä»ĺ
    0.07
    à¸Ħะà¹ģà¸Ļà¸Ļ
    0.07
    å¤ļåıĺ
    0.07
    Activations Density 0.122%

    No Known Activations