© 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. 31891
    Prev
    Next
    INDEX
    Explanations

    numbers and hyphens

    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
    ë²łìĿ´ìĬ¤
    -0.08
    .mixin
    -0.08
    æľĪ以æĿ¥
    -0.07
     Dez
    -0.07
    æķĮ
    -0.07
    .bp
    -0.07
    âĨĵâĨĵ
    -0.07
    lew
    -0.07
    æľĪèĩ³ä»Ĭ
    -0.07
     nurs
    -0.07
    POSITIVE LOGITS
    resses
    0.06
    ersp
    0.06
    Nation
    0.06
    æĹ¥çĶŁ
    0.06
    جت
    0.06
    ervi
    0.06
     Supplement
    0.06
    ataires
    0.06
     Estud
    0.06
    åĢ¾æĥħ
    0.06
    Activations Density 0.036%

    No Known Activations