© 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. 57219
    Prev
    Next
    INDEX
    Explanations

    .png files in JSON/XML lists

    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
    ä¹ĭä¸ī
    -0.07
    abus
    -0.07
    OLT
    -0.07
    rello
    -0.07
    øre
    -0.07
    åķ¡
    -0.07
    ona
    -0.07
    ä¹±
    -0.07
    äºij
    -0.07
    ·
    -0.07
    POSITIVE LOGITS
    åŁİå¸ĤåĴĮ
    0.08
    !:
    0.07
    목ìĿĦ
    0.06
    견
    0.06
    åıij表æĪĸ
    0.06
    _pwd
    0.06
    fum
    0.06
    ä»°
    0.06
    该åĨħ容
    0.06
    è¯ŃéŁ³æŶéķ¿
    0.06
    Activations Density 0.015%

    No Known Activations