© 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. 39217
    Prev
    Next
    INDEX
    Explanations

    names, dates, numbers, initials, logos

    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
    件ä¸Ń
    -0.08
    æĢĢæı£
    -0.08
    views
    -0.08
    udan
    -0.08
    _episodes
    -0.07
    å¤ļåĬ¨
    -0.07
    å¿ĥåŃĺ
    -0.07
    ANNOT
    -0.07
    æľī太å¤ļ
    -0.07
    (strict
    -0.07
    POSITIVE LOGITS
     recognizable
    0.08
    åŃĹæł·
    0.08
    æ°´åį°
    0.08
     prominently
    0.08
     initials
    0.08
    ãĤĴ示
    0.07
    çĽijåĪ¶
    0.07
    /version
    0.07
     unmistak
    0.07
     logo
    0.07
    Activations Density 0.136%

    No Known Activations