© 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. 61924
    Prev
    Next
    INDEX
    Explanations

    code blocks or variable 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
    batim
    -0.08
    ìŀł
    -0.08
    ibo
    -0.07
    è§Ĵ度çľĭ
    -0.07
    incy
    -0.07
    UAR
    -0.07
    åı¥è¯Ŀ说
    -0.07
    iggio
    -0.07
    åħįè´¹éĢģ
    -0.07
    åĴĮä¸Ĭæµ·
    -0.07
    POSITIVE LOGITS
     Pera
    0.07
     enam
    0.07
    åºŁ
    0.07
    inig
    0.06
     Äijặn
    0.06
    elt
    0.06
     {}).
    0.06
    वार
    0.06
     )))
    0.06
    èıı
    0.06
    Activations Density 0.003%

    No Known Activations