© 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. 41607
    Prev
    Next
    INDEX
    Explanations

    Oreo, silver, terminals, container, 9

    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
    åħģ
    -0.09
    ...",
    -0.07
    ê±°
    -0.07
     etc
    -0.07
    æ³ķçŃī
    -0.06
    RTL
    -0.06
    inium
    -0.06
     py
    -0.06
    ׼×ķ
    -0.06
    æĥħåĨµçŃī
    -0.06
    POSITIVE LOGITS
    对个人
    0.07
    kar
    0.07
    odoro
    0.07
    aros
    0.07
    æt
    0.07
    edith
    0.07
     rán
    0.07
    ä¼ĺçĤ¹æĺ¯
    0.06
    é®®
    0.06
    лип
    0.06
    Activations Density 0.010%

    No Known Activations