© 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. 9213
    Prev
    Next
    INDEX
    Explanations

    manager and user

    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
     Scrolls
    -0.08
    rophic
    -0.07
    encer
    -0.07
    venu
    -0.07
     tbody
    -0.07
    Ĩµ
    -0.07
    以轻
    -0.07
    werpen
    -0.06
    lesa
    -0.06
    ria
    -0.06
    POSITIVE LOGITS
    åĩij
    0.08
    à¯įதà¯įத
    0.07
    spl
    0.07
     miscellaneous
    0.07
    å·¥ä½ľäººåijĺçļĦ
    0.07
    .script
    0.07
    ä¹Łä¸įçŁ¥
    0.06
    রà§įত
    0.06
    å¸Ĥåľºçݯå¢ĥ
    0.06
     gesta
    0.06
    Activations Density 0.002%

    No Known Activations