© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46497
    Prev
    Next
    INDEX
    Explanations

    authors' initials or short names

    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
    æĸ¯é¡¿
    -0.07
    è§Ħ
    -0.07
    ä¾Ľ
    -0.07
    åľŁ
    -0.07
    /cs
    -0.06
    èĦ
    -0.06
     Maire
    -0.06
    å»ĥ
    -0.06
    å¸ļ
    -0.06
    ":""
    -0.06
    POSITIVE LOGITS
     ÐļÑĢаÑģи
    0.09
    jern
    0.08
    ulle
    0.08
    _et
    0.08
     Eisen
    0.07
     et
    0.07
    EMON
    0.07
    æľ¬æĸĩæĿ¥èĩª
    0.07
    reek
    0.07
    ç«ĭåį³ä¸ĭè½½
    0.07
    Activations Density 0.076%

    No Known Activations