© 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. 2134
    Prev
    Next
    INDEX
    Explanations

    umb

    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
    -0.08
     fix
    -0.06
     do
    -0.06
     Do
    -0.06
     (
    -0.06
     nah
    -0.06
    ↵
    -0.06
     &
    -0.06
    or
    -0.06
     usual
    -0.06
    POSITIVE LOGITS
    继ç»Ń沿
    0.09
    èĴĤæĸ¯
    0.09
    weiler
    0.09
    HEME
    0.09
    zap
    0.09
    arde
    0.09
    建ç«ĭä¸Ģ个
    0.08
    दार
    0.08
    帮åĬ©æĪij们
    0.08
    quette
    0.08
    Activations Density 0.066%

    No Known Activations