© 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. 43268
    Prev
    Next
    INDEX
    Explanations

    application state changes

    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
    æĺ¯èĩªå·±çļĦ
    -0.06
    unkt
    -0.06
    rent
    -0.06
    寻
    -0.06
    /vendor
    -0.06
    æĤī
    -0.06
    vid
    -0.06
    è¿Ļ个æķ°åŃĹ
    -0.06
    enk
    -0.06
    .gradle
    -0.06
    POSITIVE LOGITS
    embe
    0.08
    cina
    0.08
    è¶Ĭå¤ļ
    0.08
    åij¤
    0.07
    anci
    0.07
    orget
    0.07
    olz
    0.07
    czes
    0.07
    .RunWith
    0.07
    óta
    0.07
    Activations Density 0.002%

    No Known Activations