© 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. 1671
    Prev
    Next
    INDEX
    Explanations

    start of introduction

    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
    çģ«
    -0.08
    erals
    -0.07
    åıªæľīèĩªå·±
    -0.07
    uros
    -0.07
    æµĭ
    -0.07
    епен
    -0.06
    eih
    -0.06
    å¯Ł
    -0.06
    ุà¸ĩ
    -0.06
    çģ°
    -0.06
    POSITIVE LOGITS
    å©ķ
    0.07
     Lai
    0.07
    ãĤĤãĤĬ
    0.07
     vét
    0.07
    ONES
    0.07
    .prototype
    0.06
    ortes
    0.06
    æĸ°æīĭ
    0.06
    edel
    0.06
    åĴ¸é±¼
    0.06
    Activations Density 0.289%

    No Known Activations