© 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. 11102
    Prev
    Next
    INDEX
    Explanations

    to write, solve, know, expand, extract

    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¿Ŀ
    -0.08
    ][-
    -0.08
    ׼×ķ׾
    -0.07
     thereof
    -0.07
    ä¹³
    -0.07
    åı¯åIJij
    -0.07
     Prós
    -0.07
     Zaw
    -0.07
    Ĩ
    -0.07
    ucker
    -0.07
    POSITIVE LOGITS
    a
    0.07
    uby
    0.06
    æķĽ
    0.06
    æ°ıãģĮ
    0.06
    oja
    0.06
    ä»ĬæľĿ
    0.06
    èī³éĺ³
    0.06
    rief
    0.06
    Ñĥк
    0.06
    ownie
    0.06
    Activations Density 0.004%

    No Known Activations