© 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. 60955
    Prev
    Next
    INDEX
    Explanations

    numbers and currency amounts

    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
    åįĥåı¤
    -0.07
    éĶĻ失
    -0.07
    lox
    -0.06
    æĦıå¤ĸçļĦ
    -0.06
    uck
    -0.06
    åŃIJ
    -0.06
    ä¸ĬåĬł
    -0.06
     ser
    -0.06
    è¾ľè´Ł
    -0.06
    áĭ«
    -0.06
    POSITIVE LOGITS
     nub
    0.08
    zal
    0.08
    ldb
    0.08
    å¹³éĺ³
    0.08
    udge
    0.08
    ecto
    0.07
    edig
    0.07
    esting
    0.07
    imenti
    0.07
    رÙĩ
    0.07
    Activations Density 0.005%

    No Known Activations