© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 27066
    Prev
    Next
    INDEX
    Explanations

    Blur, Carlton, Purple

    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
    ame
    -0.08
    anza
    -0.07
    MMMM
    -0.07
    æ·ĺ
    -0.07
    ane
    -0.06
    诸侯
    -0.06
    è´¥
    -0.06
    anes
    -0.06
    reme
    -0.06
    bo
    -0.06
    POSITIVE LOGITS
    å°ıæķħäºĭ
    0.08
    aldas
    0.08
    ä¸İæľ¬ç«Ļ
    0.08
    èIJ±
    0.08
    alitas
    0.08
    istin
    0.07
    hluk
    0.07
    धान
    0.07
    ixe
    0.07
    matchCondition
    0.07
    Activations Density 0.268%

    No Known Activations