© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63098
    Prev
    Next
    INDEX
    Explanations

    programming terms and code constructs

    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
    ζε
    -0.07
    гÑĢо
    -0.06
    åĤ¬äºº
    -0.06
    wth
    -0.06
    sdale
    -0.06
    ulton
    -0.06
    -bg
    -0.06
    ISC
    -0.06
    åľ¨å¼Ģå±ķ
    -0.06
    ivu
    -0.06
    POSITIVE LOGITS
    rets
    0.08
    sy
    0.07
    ongs
    0.07
    ostat
    0.07
    çĴĥ
    0.07
     rasse
    0.07
    ongsTo
    0.07
    ablish
    0.07
    åħĪåĪ°
    0.07
    urent
    0.07
    Activations Density 0.184%

    No Known Activations