© 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. 31857
    Prev
    Next
    INDEX
    Explanations

    non-English names and texts

    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
    лÑĮ
    -0.07
    zwi
    -0.07
    mals
    -0.07
    æĢ»ä¸įèĥ½
    -0.07
    .lv
    -0.07
    etheless
    -0.07
    çĥŃæĥħåĴĮ
    -0.07
    jons
    -0.07
    ledge
    -0.07
    etros
    -0.07
    POSITIVE LOGITS
     keper
    0.07
    ķ
    0.07
    angel
    0.07
    ש×Ļ
    0.06
    ģ
    0.06
     specta
    0.06
    æ·ĩ
    0.06
    ollo
    0.06
    isque
    0.06
    ä¸Ńåİ»
    0.06
    Activations Density 0.090%

    No Known Activations