© 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. 50640
    Prev
    Next
    INDEX
    Explanations

    separate, stored, contained

    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
    幸
    -0.08
    éij½
    -0.07
    .tie
    -0.07
    ;base
    -0.07
    ucky
    -0.07
    æĽ´å¤ļ精彩
    -0.07
    åİŁçīĪ
    -0.07
    æĭĽèģĺåħ¬åijĬ
    -0.07
    arc
    -0.07
    ertz
    -0.07
    POSITIVE LOGITS
     tersendiri
    0.11
     separate
    0.11
     оÑĤделÑĮ
    0.10
     seperate
    0.09
     aparte
    0.09
     separado
    0.09
     Separate
    0.08
     separated
    0.08
    ãģĵãģ¡ãĤī
    0.08
     ë³ĦëıĦìĿĺ
    0.08
    Activations Density 0.519%

    No Known Activations