© 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. 3497
    Prev
    Next
    INDEX
    Explanations

    mathematical/scientific notation or acronyms

    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
    å·¥ä¸ļåįıä¼ļ
    -0.07
    éģ£
    -0.07
    æ±Ĺ
    -0.07
    zul
    -0.06
    _HIDE
    -0.06
    ÙĨاÙħÙĩ
    -0.06
    egger
    -0.06
    hec
    -0.06
    -plan
    -0.06
    ä¸Ģæİ¢
    -0.06
    POSITIVE LOGITS
    åľ¨æŃ¤åŁºç¡Ģä¸Ĭ
    0.10
    åį«ä¸ľ
    0.08
    ä¹Łä¸įä¾ĭå¤ĸ
    0.08
    åĬłäºĨ
    0.08
    çijľ
    0.07
    ordes
    0.07
     introduc
    0.07
    è¦ı模
    0.07
    以æŃ¤ä¸º
    0.07
    armed
    0.07
    Activations Density 0.030%

    No Known Activations