© 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. 39962
    Prev
    Next
    INDEX
    Explanations

    ãģĹãģ¦ / that

    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
    otto
    -0.09
    ogne
    -0.09
    pio
    -0.09
    çĦ¶æĺ¯
    -0.09
    mio
    -0.08
    után
    -0.08
    orrow
    -0.08
    arrer
    -0.08
    ally
    -0.08
    ////////////////////////////////////////////////////////////////
    -0.08
    POSITIVE LOGITS
    ingle
    0.07
    ÑģÑı
    0.07
    ìĦľëĬĶ
    0.07
    oji
    0.07
    INGS
    0.07
    ejas
    0.06
    Ø¡
    0.06
    人å¿ĥçļĦ
    0.06
    ÑģÑĮ
    0.06
    리ì¦ĺ
    0.06
    Activations Density 0.005%

    No Known Activations