© 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. 38145
    Prev
    Next
    INDEX
    Explanations

    answering questions and providing help

    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
    iato
    -0.07
    巨人
    -0.07
    alue
    -0.07
    åĪ©äºİ
    -0.07
    iec
    -0.07
    alty
    -0.07
    æīĢå±ŀ
    -0.06
    iews
    -0.06
    .bs
    -0.06
    RuntimeException
    -0.06
    POSITIVE LOGITS
    eggio
    0.07
    ỡ
    0.07
    åį³å°ĨæĿ¥ä¸´
    0.07
    à°¹
    0.07
    ìĦľ
    0.06
    elda
    0.06
    obox
    0.06
    itazioni
    0.06
    çĶ¨çº¸
    0.06
    ogue
    0.06
    Activations Density 0.001%

    No Known Activations