© 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. 13484
    Prev
    Next
    INDEX
    Explanations

    diffraction structures

    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
    ož
    -0.08
    缮çŀª
    -0.08
    onyme
    -0.07
    Fixture
    -0.07
    _CYCLE
    -0.07
    _DEFINED
    -0.07
    ยà¹Į
    -0.07
    ÏĦζ
    -0.07
    дж
    -0.07
    ÙijاÙĭ
    -0.07
    POSITIVE LOGITS
    erschein
    0.09
    umat
    0.08
    alow
    0.07
    lom
    0.07
     Auff
    0.07
    -free
    0.07
    ç»ķ
    0.07
    ç»ķè¿ĩ
    0.07
    resenter
    0.06
    коÑĤ
    0.06
    Activations Density 0.004%

    No Known Activations