© 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. 61842
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and programming context

    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
    åIJijèį£
    -0.09
    kiye
    -0.08
    èī²åĪĹ
    -0.08
    æł©
    -0.08
    getCell
    -0.07
    preso
    -0.07
     retired
    -0.07
    åŁŁç½ij
    -0.07
    akeup
    -0.07
    ocket
    -0.07
    POSITIVE LOGITS
    idue
    0.06
     Earn
    0.06
     discontin
    0.06
    onis
    0.06
    तà¥į
    0.06
     onBlur
    0.06
     triá»ĩt
    0.06
     sinc
    0.06
    Earn
    0.06
    rick
    0.06
    Activations Density 0.018%

    No Known Activations