© 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. 23392
    Prev
    Next
    INDEX
    Explanations

    silicon (Si) and icon-based technologies

    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
    lier
    -0.08
    htable
    -0.07
    ä¸įæĥĬ
    -0.07
    ä¹ħèĢĮ
    -0.07
    abbo
    -0.07
    lopen
    -0.07
    å¾Ĺèµ·
    -0.06
    nel
    -0.06
    ×ķ×ķ
    -0.06
     Jasa
    -0.06
    POSITIVE LOGITS
     dioxide
    0.10
    arella
    0.10
    éħ¸çĽIJ
    0.08
     sót
    0.08
    erber
    0.08
    emens
    0.07
    ène
    0.07
    anit
    0.07
    çĴĭ
    0.07
    endale
    0.07
    Activations Density 0.031%

    No Known Activations