© 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. 9348
    Prev
    Next
    INDEX
    Explanations

    initial conditions or base cases

    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»İåħ¶
    -0.09
    åŃ£åIJİ
    -0.08
    ientos
    -0.08
    ibat
    -0.08
     spe
    -0.08
    为主导
    -0.07
    主åĬŀ
    -0.07
    è¿Ļ个åĵģçīĮ
    -0.07
    lopedia
    -0.07
    essenger
    -0.07
    POSITIVE LOGITS
    åĪĿ
    0.09
     trivial
    0.07
     Initialization
    0.07
     simplest
    0.07
     initial
    0.06
    Initialization
    0.06
    交å¾ħ
    0.06
    ØŃÙĦØ©
    0.06
    æ£ĢéªĮ
    0.06
    åĪĿå§ĭ
    0.06
    Activations Density 0.003%

    No Known Activations