© 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. 26493
    Prev
    Next
    INDEX
    Explanations

    film and document contexts

    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
    æİĸ
    -0.07
    ople
    -0.07
    chter
    -0.07
     Arbitrary
    -0.07
     unquestion
    -0.07
    taire
    -0.07
     råd
    -0.06
    Ùĩرب
    -0.06
    èĢĮå¤į
    -0.06
    oid
    -0.06
    POSITIVE LOGITS
    afil
    0.07
    argo
    0.07
     costum
    0.07
     informat
    0.07
    æĬķèµĦæĪĸ
    0.07
     futur
    0.07
    мам
    0.07
    amon
    0.07
    fil
    0.06
    ãģ¾ãģ¨
    0.06
    Activations Density 0.012%

    No Known Activations