© 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. 45251
    Prev
    Next
    INDEX
    Explanations

    code syntax and symbols

    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
    è¶ģ
    -0.08
    opr
    -0.07
    è¶ģçĿĢ
    -0.07
    Æ¡
    -0.07
    å¿į
    -0.07
    teis
    -0.07
    éªı
    -0.07
    anz
    -0.06
    ô
    -0.06
    æ¼±åı£
    -0.06
    POSITIVE LOGITS
    ä»Ģ
    0.08
    esse
    0.07
    ingan
    0.07
    æľīè¯Ŀ
    0.07
     daw
    0.07
    etsk
    0.06
    ä½łåij¢
    0.06
    ekl
    0.06
     Scri
    0.06
    uvan
    0.06
    Activations Density 0.003%

    No Known Activations