© 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. 51828
    Prev
    Next
    INDEX
    Explanations

    difference, ratio, gap

    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
    ãģĤãĤĬ
    -0.07
    ourd
    -0.06
     Words
    -0.06
    empty
    -0.06
     X
    -0.06
    åħ·ä½ĵåĨħ容
    -0.06
    御
    -0.06
    æĸ¹æ³ķåıĬ
    -0.06
    ANGO
    -0.06
    çŁŃæŶ
    -0.06
    POSITIVE LOGITS
     difference
    0.15
    å·®
    0.15
    å·®çļĦ
    0.13
     Difference
    0.13
    difference
    0.13
     differences
    0.13
    å·®è·Ŀ
    0.13
     gap
    0.12
    _difference
    0.12
    ä¹ĭå·®
    0.12
    Activations Density 0.029%

    No Known Activations