© 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. 1727
    Prev
    Next
    INDEX
    Explanations

    water level

    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
    æĢĿæĥ³ä¸Ĭ
    -0.08
    utte
    -0.08
    åľ¨æĢĿæĥ³ä¸Ĭ
    -0.08
    å±ħæĺĵ
    -0.08
    Ú©ÛĮÙĦ
    -0.08
    夫åŃIJ
    -0.07
    deles
    -0.07
     baggage
    -0.07
     synthes
    -0.07
    çĭ¬è¡Į
    -0.07
    POSITIVE LOGITS
     height
    0.10
    æ°´ä½į
    0.10
    液ä½į
    0.10
     heights
    0.10
    height
    0.10
    é«ĺ度
    0.09
    -height
    0.09
     Height
    0.09
    Height
    0.09
    çļĦé«ĺ度
    0.09
    Activations Density 0.032%

    No Known Activations