© 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. 25027
    Prev
    Next
    INDEX
    Explanations

    ORDER, publication, regulated

    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
     Plen
    -0.08
    天边
    -0.08
    åıijå±ķä¸İ
    -0.08
     kle
    -0.08
    å®ŀéĻħéľĢè¦ģ
    -0.08
    æĸ°åıijå±ķ
    -0.07
    emsp
    -0.07
    å¤įå·¥
    -0.07
     nevoie
    -0.07
    æ²³ä¸Ń
    -0.07
    POSITIVE LOGITS
    .rstrip
    0.06
     (...)
    0.06
    åĪĨåĩº
    0.06
    صÙĦ
    0.06
    vation
    0.06
    åıĺ
    0.06
    åľĪ
    0.06
    Ti
    0.06
    缸äºĴ
    0.05
     mean
    0.05
    Activations Density 0.048%

    No Known Activations