© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14757
    Prev
    Next
    INDEX
    Explanations

    scientific notation/measurement

    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
    en
    -0.14
    Ùĩ
    -0.12
    es
    -0.11
    åĬłæĭ¿å¤§
    -0.10
    al
    -0.10
    ÑģÑĮ
    -0.10
    er
    -0.09
    i
    -0.09
    à¯į
    -0.09
    ation
    -0.09
    POSITIVE LOGITS
    ï¸İ
    0.13
    ¯
    0.11
    ħ
    0.11
    ————————————————
    0.10
    sprach
    0.10
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    0.09
    schen
    0.09
    ¦
    0.08
    elper
    0.08
    à¸Ļาà¸ģาร
    0.08
    Activations Density 0.002%

    No Known Activations