© 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. 30015
    Prev
    Next
    INDEX
    Explanations

    acting

    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
    urd
    -0.07
    bah
    -0.07
    åĴĮçĶ°
    -0.06
    å¹´éĿĴ
    -0.06
    urrencies
    -0.06
     bah
    -0.06
    heber
    -0.06
     Yıld
    -0.06
     petró
    -0.06
    niÄį
    -0.06
    POSITIVE LOGITS
    olle
    0.09
    igar
    0.08
     jakim
    0.08
    ÂŃing
    0.07
    çİ¥
    0.07
    Ñĺи
    0.07
    åı«åģļ
    0.07
    ulp
    0.07
    apper
    0.07
    atti
    0.07
    Activations Density 0.341%

    No Known Activations