© 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. 48252
    Prev
    Next
    INDEX
    Explanations

    sentences starting with "it"

    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
    åĩı
    -0.08
    éĢIJ
    -0.07
    colari
    -0.07
    kannt
    -0.07
    寡
    -0.06
    éĢı
    -0.06
    reau
    -0.06
    å¹»
    -0.06
    æľ«
    -0.06
     suur
    -0.06
    POSITIVE LOGITS
    asin
    0.08
    主é¢ĺæĽ²
    0.08
    achs
    0.07
    ozo
    0.07
    åIJ¹é£İ
    0.07
    é«ĺåľ°
    0.07
    èĢĮçĶŁ
    0.07
    мелÑĮ
    0.07
    ice
    0.07
     bom
    0.07
    Activations Density 0.134%

    No Known Activations