© 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. 15260
    Prev
    Next
    INDEX
    Explanations

    IP addresses and ranges

    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
    为åįķä½į
    -0.06
    öse
    -0.06
    æĮ¥
    -0.06
    åĶ
    -0.06
    uel
    -0.06
    è´
    -0.06
    animations
    -0.06
    缼
    -0.06
     roy
    -0.06
    eka
    -0.06
    POSITIVE LOGITS
    веÑĢо
    0.09
    ycz
    0.09
    èĭ¦è¾£
    0.08
    ivant
    0.08
    Ñijн
    0.07
    zien
    0.07
    intes
    0.07
    Kota
    0.07
    imers
    0.07
    iner
    0.07
    Activations Density 0.013%

    No Known Activations