© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33113
    Prev
    Next
    INDEX
    Explanations

    digit sequences or separators

    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
    ubar
    -0.06
     eyed
    -0.06
    chtig
    -0.06
    å¾Ĺä¸į
    -0.06
    说ä¸įåĩºçļĦ
    -0.06
     Myst
    -0.06
    对å¾ħ
    -0.06
    RIOS
    -0.06
     Them
    -0.06
    angani
    -0.06
    POSITIVE LOGITS
    IBIL
    0.08
    elope
    0.08
    ","+
    0.07
    licit
    0.07
    åĸľæĢĴåĵĢ
    0.07
    boa
    0.07
    çħ¦
    0.07
    åIJĦç§įåIJĦæł·
    0.07
    ursion
    0.07
    åĺĺ
    0.07
    Activations Density 0.009%

    No Known Activations