© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 41342
    Prev
    Next
    INDEX
    Explanations

    dates, numbers, and units

    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
    åĿļåĽº
    -0.07
    nun
    -0.07
    opi
    -0.07
    æĺĨ
    -0.07
     passwd
    -0.07
    uiltin
    -0.07
    uji
    -0.07
    åľ¨ç»ıæµİ
    -0.07
    ä¸įèĥ½å®Įåħ¨
    -0.07
    绣çѹæİ¨è¿Ľ
    -0.06
    POSITIVE LOGITS
    对åºĶ
    0.10
    对åºĶçļĦ
    0.10
     corresponding
    0.10
     correspond
    0.08
     corresponds
    0.08
     corres
    0.08
    çĽ¸å¯¹åºĶçļĦ
    0.08
     correspondant
    0.08
     Correspond
    0.08
    å°įæĩī
    0.08
    Activations Density 0.186%

    No Known Activations