© 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. 63451
    Prev
    Next
    INDEX
    Explanations

    specific words or phrases

    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
    [âĢ¦]
    -0.08
    ambre
    -0.08
    人èĥ½
    -0.08
    ugins
    -0.07
    resident
    -0.07
    jala
    -0.07
    æ°§åĮĸ碳
    -0.07
     Citt
    -0.07
    ypy
    -0.07
    plen
    -0.07
    POSITIVE LOGITS
    orada
    0.07
    eniu
    0.07
    Ĭ
    0.07
    ÏĮδ
    0.07
    idot
    0.07
    æĴ
    0.06
    ij
    0.06
    å¤§æ±Ł
    0.06
    åĴĮä¸Ĭæµ·
    0.06
    weit
    0.06
    Activations Density 0.019%

    No Known Activations