© 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. 32166
    Prev
    Next
    INDEX
    Explanations

    studio for, product for, tuned in

    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
    ä¸Ĭæĸ°åı°éĺ¶
    -0.08
    åĿĤ
    -0.08
    æľ¬ç«ĻæīĢæľī
    -0.08
    leftright
    -0.08
    iggers
    -0.08
    aporte
    -0.08
    翼翼
    -0.08
    Ľ
    -0.08
    lacement
    -0.07
    à¸ģรุ
    -0.07
    POSITIVE LOGITS
    åı¸
    0.06
     impress
    0.06
    arden
    0.06
    åĪ°åºķ
    0.06
     beaten
    0.06
     beats
    0.06
    åIJīæĸ¯
    0.06
    汽车éħį件
    0.06
     Dinner
    0.06
    eer
    0.06
    Activations Density 0.970%

    No Known Activations