© 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. 45115
    Prev
    Next
    INDEX
    Explanations

    orientation mode

    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
    è¨Ģéģĵ
    -0.07
    缴æİ¥åIJij
    -0.07
    VIP
    -0.07
     moments
    -0.07
    ç§įåħ»
    -0.06
    лина
    -0.06
    ring
    -0.06
    æ±°
    -0.06
     vip
    -0.06
    ç»ı常æĢ§
    -0.06
    POSITIVE LOGITS
    anium
    0.08
    ativa
    0.08
    Defaults
    0.07
    imson
    0.07
    اÛĮØ´
    0.07
    é»ĺ认
    0.07
    _default
    0.07
    åıĸèĪį
    0.07
     prevailing
    0.07
    isti
    0.07
    Activations Density 0.001%

    No Known Activations