© 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. 49694
    Prev
    Next
    INDEX
    Explanations

    page-down, second, dog, Jill

    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
    riel
    -0.09
    okin
    -0.08
    èĬ±æł·
    -0.07
    /pp
    -0.07
    èĢĮå¤į
    -0.07
    æĸĻçļĦ
    -0.07
    è½½
    -0.07
    檩
    -0.07
    ATA
    -0.07
    RITE
    -0.07
    POSITIVE LOGITS
    æķı
    0.07
    ä¸įæĸŃåıijå±ķ
    0.07
    家ä¸Ń
    0.06
    peria
    0.06
    getElement
    0.06
     Act
    0.06
    çľĭä¸Ń
    0.06
    è§ĤæľĽ
    0.06
    otron
    0.06
     League
    0.06
    Activations Density 0.048%

    No Known Activations