© 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. 3560
    Prev
    Next
    INDEX
    Explanations

    content, data, books, skills, needs

    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
    hower
    -0.08
    soever
    -0.07
    缸è¾ħ缸æĪIJ
    -0.07
    htub
    -0.07
    ÙĨÛĮÙĨ
    -0.07
    uille
    -0.07
    aeda
    -0.06
    aney
    -0.06
    åį³çĶ¨
    -0.06
     nutshell
    -0.06
    POSITIVE LOGITS
    'autres
    0.07
    å¤ĸçļĦ
    0.07
    çļĦåIJĮæŶ
    0.07
    ãģ«ãĤĪãģ£ãģ¦ãģ¯
    0.07
    azel
    0.07
    idou
    0.07
    åĴĮ责任
    0.07
     Sunshine
    0.07
    illions
    0.07
    ä¸įå®ļ
    0.07
    Activations Density 0.352%

    No Known Activations