© 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. 7723
    Prev
    Next
    INDEX
    Explanations

    chapter or table numbers

    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
     hÃłn
    -0.07
    دÙĩ
    -0.07
    ilde
    -0.07
    ä½ľçļĦ
    -0.06
    ë¡
    -0.06
    pts
    -0.06
    kd
    -0.06
    <!--
    -0.06
    çħ§çĿĢ
    -0.06
    alia
    -0.06
    POSITIVE LOGITS
    ostream
    0.08
    resher
    0.07
    -decoration
    0.07
    stes
    0.06
     sourceMappingURL
    0.06
    车å¸Ĥ
    0.06
    ÑģÑĤÑĢе
    0.06
    bbing
    0.06
    звание
    0.06
    ponge
    0.06
    Activations Density 0.066%

    No Known Activations