© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15865
    Prev
    Next
    INDEX
    Explanations

    volume or amount of liquid

    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
     mosa
    -0.07
    èĩªå·±èº«ä¸Ĭ
    -0.07
    omon
    -0.07
    æĽ´è¿Ľä¸ĢæŃ¥
    -0.07
    èĩªå·±æľī
    -0.06
    æĺİæĺ¾æıIJé«ĺ
    -0.06
    ooke
    -0.06
    ufe
    -0.06
    elig
    -0.06
    éĢģèµ°
    -0.06
    POSITIVE LOGITS
    äºĭåħĪ
    0.08
    æ³
    0.08
     appropriate
    0.07
    æ°´éĩı
    0.07
    initial
    0.07
    éĢĤå®ľçļĦ
    0.07
    éĢĤéĩıçļĦ
    0.07
    æ°´åĴĮ
    0.07
    .reverse
    0.07
    idla
    0.07
    Activations Density 0.021%

    No Known Activations