© 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. 61404
    Prev
    Next
    INDEX
    Explanations

    color and flavor

    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
    keb
    -0.08
    å¥ł
    -0.07
    ยาà¸ģ
    -0.07
    å°Ķåħĭ
    -0.07
    atee
    -0.07
    ¨
    -0.07
    istani
    -0.07
     sti
    -0.07
    tings
    -0.07
    otherapy
    -0.07
    POSITIVE LOGITS
    oop
    0.07
    ิà¹īม
    0.07
    isca
    0.07
    OUS
    0.06
    odox
    0.06
    ously
    0.06
    ê¹
    0.06
    loh
    0.06
    -specific
    0.06
    ç»ıæµİåѦ
    0.06
    Activations Density 0.001%

    No Known Activations