© 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. 8575
    Prev
    Next
    INDEX
    Explanations

    persistent luminescence removal

    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
    åĪĨåĮĸ
    -0.08
    koch
    -0.08
     Modena
    -0.08
    æ¶ĪåĮĸçļĦ
    -0.07
     Regione
    -0.07
    建ä¸ļ
    -0.07
    .SDK
    -0.07
    ÏĨι
    -0.07
    erville
    -0.07
    çİĭåºľ
    -0.07
    POSITIVE LOGITS
    ...
    0.07
    æľ¬æ³ķ
    0.07
    _obj
    0.06
    uket
    0.06
    resso
    0.06
    unks
    0.06
    attern
    0.06
    ÃŃce
    0.06
    æĿ¥æĿ¥
    0.06
    _tem
    0.06
    Activations Density 0.446%

    No Known Activations