© 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. 2067
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers, integers, or enumeration

    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
    ëŀĮ
    -0.09
    @a
    -0.08
    PRINTF
    -0.08
    itul
    -0.08
    èĥİ
    -0.07
    [âĢ¦
    -0.07
    <decltype
    -0.07
    åľ¨åħ¨çľģ
    -0.07
    ä¸ĢæĶ¹
    -0.07
    çļĦåIJĪæĪIJ
    -0.07
    POSITIVE LOGITS
    integer
    0.07
     numbering
    0.07
     integer
    0.07
    ä¼ĺèĥľ
    0.06
     Enumeration
    0.06
     regular
    0.06
     indexing
    0.06
    é¬
    0.06
    çķªåı·
    0.06
    ivery
    0.06
    Activations Density 0.005%

    No Known Activations