© 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. 55465
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    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
     McKay
    -0.06
    ori
    -0.06
    nu
    -0.06
    fila
    -0.06
    fil
    -0.06
    prof
    -0.06
     diss
    -0.06
     nipples
    -0.06
     Reinh
    -0.06
    ese
    -0.06
    POSITIVE LOGITS
    Ñģпа
    0.07
    碼
    0.07
    ç»Ŀä¸ĸ
    0.07
    enges
    0.07
    oksi
    0.07
    epam
    0.07
    夫æĸ¯åŁº
    0.07
    TestMethod
    0.07
     lá»Ńa
    0.07
    å·¾
    0.07
    Activations Density 0.002%

    No Known Activations