© 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. 7973
    Prev
    Next
    INDEX
    Explanations

    web path navigation

    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
    opedia
    -0.08
    erat
    -0.07
    å¥ķ
    -0.07
    imers
    -0.07
    icias
    -0.07
    esten
    -0.07
    elan
    -0.07
    utile
    -0.07
    åºĶçĶ¨é¢ĨåŁŁ
    -0.07
    åºĶçĶ¨
    -0.07
    POSITIVE LOGITS
    /or
    0.14
    /o
    0.11
    /OR
    0.10
     vice
    0.09
    å¾Ģ常ä¸Ģæł·
    0.08
    ients
    0.08
    _then
    0.08
    orra
    0.08
    ÑĢак
    0.08
    AndGet
    0.08
    Activations Density 0.286%

    No Known Activations