© 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. 61430
    Prev
    Next
    INDEX
    Explanations

    way,

    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
    ä¹Łä¸įè¡Į
    -0.07
    äºİæĺ¯ä»ĸ
    -0.07
    åĴ¨è¯¢æĪij
    -0.07
    ç´įå¾Ĺ
    -0.07
    ohn
    -0.07
    ä»ĭç»į说
    -0.07
    帮大家
    -0.07
    沿è¡Ĺ
    -0.06
     impun
    -0.06
    åķ§åķ§
    -0.06
    POSITIVE LOGITS
     sincer
    0.09
    è¡·
    0.09
    è¯ļæĮļ
    0.08
    é¡ĺ
    0.08
    继ç»Ńä¿ĿæĮģ
    0.08
     hereby
    0.08
    å¸ĮæľĽä½łä»¬
    0.08
    incerely
    0.08
     sincerely
    0.08
    ä¹Łå¸ĮæľĽ
    0.08
    Activations Density 0.627%

    No Known Activations