© 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. 43918
    Prev
    Next
    INDEX
    Explanations

    numbers and mathematical expressions

    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
    åĪ¤åĨ³ä¹¦
    -0.06
    åĨįåĬłä¸Ĭ
    -0.06
    isis
    -0.06
    æİĴéĻ¤
    -0.06
    ritch
    -0.06
     Kitt
    -0.06
     primaries
    -0.06
    çĭ¬å¤Ħ
    -0.06
    åĿij
    -0.06
    åĪ¤åĪij
    -0.06
    POSITIVE LOGITS
    ä¸İ被
    0.07
    uyo
    0.07
    kannt
    0.07
    ếch
    0.07
    ecten
    0.07
    VS
    0.07
    ÏĦικο
    0.07
    LayoutManager
    0.07
    ofil
    0.07
    æĥ¯äºĨ
    0.07
    Activations Density 0.001%

    No Known Activations