© 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. 43236
    Prev
    Next
    INDEX
    Explanations

    $n+1$ different sources

    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
    ÙĪØ´
    -0.08
    erÃŃa
    -0.07
    çĥŃéŨæݨèįIJ
    -0.07
    ug
    -0.07
    edList
    -0.07
    EMENT
    -0.07
    人åĪ°
    -0.07
    enom
    -0.07
     sendiri
    -0.06
    orsi
    -0.06
    POSITIVE LOGITS
    ä¸įåİĮ
    0.07
    rah
    0.07
    天水
    0.07
     Struk
    0.07
    brio
    0.07
    dap
    0.07
    ÙĦÙĬØ©
    0.07
    éºŁ
    0.07
    िल
    0.07
    oose
    0.07
    Activations Density 0.002%

    No Known Activations