© 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. 41599
    Prev
    Next
    INDEX
    Explanations

    maker street

    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
    eval
    -0.08
    otts
    -0.08
    _fixture
    -0.08
    Ñīина
    -0.07
    à¹ĥหà¹īà¸Ħวาม
    -0.07
     McK
    -0.07
    âĢ§
    -0.07
    abase
    -0.07
    abar
    -0.07
    اÙĨت
    -0.07
    POSITIVE LOGITS
    sic
    0.07
    ÙıÙħÙĴ
    0.07
    rtl
    0.06
    vely
    0.06
    ëĭĪëĭ¤
    0.06
    ?a
    0.06
    ript
    0.06
    lessly
    0.06
    iby
    0.06
    ήÏĦη
    0.06
    Activations Density 0.654%

    No Known Activations