© 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. 43008
    Prev
    Next
    INDEX
    Explanations

    arithmetic questions

    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
    brook
    -0.08
    ä¹ĸ
    -0.07
    agal
    -0.07
    anzo
    -0.07
    ansa
    -0.07
    ampaign
    -0.07
    EDIA
    -0.06
    olos
    -0.06
    ä»ĸ们没æľī
    -0.06
    iews
    -0.06
    POSITIVE LOGITS
    åĸ¶
    0.08
    etail
    0.07
    cial
    0.07
    æĪij家
    0.06
    ලà·Ĭ
    0.06
    ITION
    0.06
    inder
    0.06
    लà¥į
    0.06
    fici
    0.06
    (Abstract
    0.06
    Activations Density 0.004%

    No Known Activations