© 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. 10595
    Prev
    Next
    INDEX
    Explanations

    European names and prefixes

    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
    辺
    -0.08
    ushima
    -0.08
     backs
    -0.07
    ä¸ĩåĽ½
    -0.06
    bon
    -0.06
    èĥĮ
    -0.06
    back
    -0.06
    ledo
    -0.06
    bund
    -0.06
    imoto
    -0.06
    POSITIVE LOGITS
    ç¥Ń
    0.08
    ura
    0.08
    éric
    0.08
    uro
    0.07
    _activate
    0.07
    ureau
    0.07
    _draft
    0.07
    ãģ¾ãģĪ
    0.07
     Stéph
    0.07
    åĪ«åIJį
    0.07
    Activations Density 0.342%

    No Known Activations