© 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. 12803
    Prev
    Next
    INDEX
    Explanations

    definitively, concisely, emphatically, programmatically, verbatim, interchangeably, colloquially

    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
    çIJĨ论åĴĮ
    -0.08
    manship
    -0.08
     sheer
    -0.07
    ation
    -0.07
    mans
    -0.07
    fører
    -0.07
    onis
    -0.07
    ιά
    -0.07
    纯粹
    -0.07
    纯粹çļĦ
    -0.07
    POSITIVE LOGITS
    åĵī
    0.08
     enough
    0.08
    ily
    0.07
     nhất
    0.07
    -ish
    0.07
    ignano
    0.07
    åľ°å°Ĩ
    0.07
    ãĤĪãģĨãģ«
    0.07
    ently
    0.07
    зен
    0.06
    Activations Density 0.002%

    No Known Activations