© 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. 55812
    Prev
    Next
    INDEX
    Explanations

    separating numbers and coordinates

    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
    tte
    -0.08
    inely
    -0.07
    æĴ«
    -0.07
    åĸ³åĸ³
    -0.07
    itest
    -0.07
    :^
    -0.07
    é«ĺä½İ
    -0.07
    tter
    -0.07
    CKER
    -0.07
    .await
    -0.07
    POSITIVE LOGITS
    olim
    0.07
    whatever
    0.07
    ereo
    0.07
    åıĬ
    0.06
     whatever
    0.06
    ycz
    0.06
    没说
    0.06
    TEN
    0.06
     apapun
    0.06
    .Encoding
    0.06
    Activations Density 0.013%

    No Known Activations