© 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. 8032
    Prev
    Next
    INDEX
    Explanations

    random variation and stochasticity

    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
    ä¸įæĹ©
    -0.09
    å¤įåIJĪ
    -0.08
    å¦Ĥèį¼
    -0.07
    è¡Įäºij
    -0.07
    eworld
    -0.07
    鼨åIJİ
    -0.07
    ä¸Ģ亮
    -0.07
    è¦ģæ±Ĥèĩªå·±
    -0.07
    主ä½ĵå·¥ç¨ĭ
    -0.07
    ifold
    -0.07
    POSITIVE LOGITS
     random
    0.15
    éļıæľº
    0.14
    random
    0.14
    /random
    0.13
     Random
    0.13
     randomness
    0.13
     randomly
    0.13
    -random
    0.13
     اÙĦعش
    0.13
    Random
    0.12
    Activations Density 0.003%

    No Known Activations