© 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. 40429
    Prev
    Next
    INDEX
    Explanations

    code string formatting

    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
    dea
    -0.07
    essa
    -0.07
    éĵº
    -0.07
    äºī
    -0.07
    aye
    -0.06
    以ä¸ĭåĩł
    -0.06
    以ä¸ĭåĩłä¸ª
    -0.06
    witch
    -0.06
    inne
    -0.06
    å®ļ
    -0.06
    POSITIVE LOGITS
    zul
    0.08
     kupon
    0.08
    ç¥Ŀç¦ıä½ł
    0.07
    ziem
    0.07
    epam
    0.07
    kontak
    0.07
    kad
    0.07
    _INCLUDED
    0.07
    Ñĸз
    0.07
    ìļ°ìĬ¤
    0.07
    Activations Density 0.013%

    No Known Activations