© 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. 15385
    Prev
    Next
    INDEX
    Explanations

    perfect or right amount, size, length, timing

    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
    å¿łè¯ļ
    -0.08
    .icons
    -0.07
    åħ¨éĿ¢æıIJé«ĺ
    -0.07
    åºķ线
    -0.07
    æĹłéĹ»
    -0.07
    iriam
    -0.07
    ä¸įæĸŃ强åĮĸ
    -0.07
    强åĮĸ
    -0.06
    âī¥
    -0.06
    åľºéĿ¢
    -0.06
    POSITIVE LOGITS
    éĢĤä¸Ń
    0.17
    æģ°åĪ°å¥½å¤Ħ
    0.17
    à¸ŀà¸Ńà¸Ķี
    0.16
    æģ°åĪ°
    0.16
    åĪļåĪļ好
    0.15
    ãģ¡ãĤĩãģĨãģ©
    0.15
    åIJĪéĢĤçļĦ
    0.14
    åĪļ好
    0.14
    æŃ£å¥½
    0.13
    åIJĪéĢĤ
    0.13
    Activations Density 0.166%

    No Known Activations