© 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. 46274
    Prev
    Next
    INDEX
    Explanations

    south or west

    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
    Fort
    -0.07
    ubile
    -0.07
     Sle
    -0.07
    åĴĮ缸åħ³
    -0.07
    fort
    -0.07
    obo
    -0.07
     ØŃج
    -0.07
    fek
    -0.07
    åħ·æľī以ä¸ĭ
    -0.07
    åĴĮæľīåħ³
    -0.07
    POSITIVE LOGITS
    æģ©
    0.07
    缴æİ¥
    0.07
    çĽĬ
    0.07
    绣çŃ¹æİ¨è¿Ľ
    0.07
    ivers
    0.07
    ново
    0.07
     slight
    0.06
     Nazar
    0.06
    ÙĪÙĬس
    0.06
    å¾®ä¸į足
    0.06
    Activations Density 0.014%

    No Known Activations