© 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. 60237
    Prev
    Next
    INDEX
    Explanations

    numerals and symbols

    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
    PLIT
    -0.08
    åľ³
    -0.08
    Ïħμα
    -0.08
     *(*
    -0.08
     ván
    -0.08
    RTC
    -0.08
    åIJĮæ¯Ķå¢ŀåĬł
    -0.07
    yman
    -0.07
    é£İ声
    -0.07
    ERO
    -0.07
    POSITIVE LOGITS
     Hudson
    0.07
    çIJĨ论ä¸İå®ŀè·µ
    0.07
    èįĨ
    0.06
     impar
    0.06
    kunde
    0.06
    à¸Īำ
    0.06
    空
    0.06
    èµĦ
    0.06
    lein
    0.06
    ullen
    0.06
    Activations Density 0.396%

    No Known Activations