© 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. 21224
    Prev
    Next
    INDEX
    Explanations

    photo or pictured citation

    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
    å±±éķĩ
    -0.07
    æľīçĶŁ
    -0.07
    ukan
    -0.07
    yro
    -0.07
    æij¸æij¸
    -0.07
     sublic
    -0.07
    å©·
    -0.07
    ehl
    -0.07
     \''
    -0.07
    Indented
    -0.07
    POSITIVE LOGITS
    æĸ§
    0.08
    ieme
    0.07
    ÑĢиÑģÑĤ
    0.07
    _MACRO
    0.07
    uja
    0.07
     prezi
    0.06
    è¿ŀåIJĮ
    0.06
    åĽº
    0.06
    æŀĹ
    0.06
    åŁ
    0.06
    Activations Density 0.001%

    No Known Activations