© 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. 62103
    Prev
    Next
    INDEX
    Explanations

    currencies and their values

    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
    ãĥ§ãĥ³
    -0.08
    tock
    -0.08
    ä½įåŃIJ
    -0.07
    hing
    -0.07
    ãĤħãģĨ
    -0.07
    ller
    -0.07
    theid
    -0.07
    AEA
    -0.06
    ãĥ¥ãĥ¼
    -0.06
    над
    -0.06
    POSITIVE LOGITS
     ($)
    0.09
     ÙĨÙĤد
    0.08
    деÑģÑı
    0.08
    çīĪçļĦ
    0.07
    æµģéĢļ
    0.07
    ($)
    0.07
    éĴ±çļĦ
    0.07
    ä¿
    0.07
    izable
    0.07
     equivalent
    0.07
    Activations Density 0.039%

    No Known Activations