© 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. 62338
    Prev
    Next
    INDEX
    Explanations

    version numbers

    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
    acco
    -0.07
    ŀ
    -0.06
    æī¾çļĦ
    -0.06
    -bot
    -0.06
    欲
    -0.06
    æĪIJåĬŁåIJİåį³åı¯
    -0.06
    çĥŃæIJľè¯į
    -0.06
    mie
    -0.06
    èıĬèĬ±
    -0.06
    -scrollbar
    -0.06
    POSITIVE LOGITS
     version
    0.13
    çīĪæľ¬
    0.13
    version
    0.11
    çīĪæľ¬çļĦ
    0.11
     Version
    0.11
     versions
    0.10
    æľĢæĸ°çīĪæľ¬
    0.10
    Version
    0.10
    _version
    0.10
    -version
    0.10
    Activations Density 0.300%

    No Known Activations