© 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. 30751
    Prev
    Next
    INDEX
    Explanations

    closed sets

    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
    ield
    -0.08
    Äįe
    -0.07
    agrid
    -0.07
    apolis
    -0.07
    ä¸įåĩ¡
    -0.07
    attro
    -0.07
    Äįet
    -0.07
    æ´ŀéĩĮ
    -0.07
    æ³ķåħ°
    -0.07
    iple
    -0.07
    POSITIVE LOGITS
    ness
    0.13
    Ø©
    0.08
    اء
    0.08
    ation
    0.08
    ezas
    0.07
    æ²īæ·Ģ
    0.07
    ов
    0.07
    ç²Ľ
    0.06
    yss
    0.06
    rts
    0.06
    Activations Density 0.003%

    No Known Activations