© 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. 51803
    Prev
    Next
    INDEX
    Explanations

    shallow water, waves, pools

    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
    骨
    -0.08
    深海
    -0.08
    -0.08
    æµ·è§Ĵ
    -0.08
    åı¤å±ĭ
    -0.07
    æĬĹçĻĮ
    -0.07
    èĪªæµ·
    -0.07
    éĻ¨
    -0.07
    Target
    -0.07
     medical
    -0.07
    POSITIVE LOGITS
     runoff
    0.09
     shallow
    0.09
     drainage
    0.09
     Manning
    0.09
    IBC
    0.08
     hydraul
    0.08
    åĿ¡åº¦
    0.08
    éĻ¡
    0.08
    æ°´æ·±
    0.08
     water
    0.07
    Activations Density 0.009%

    No Known Activations