© 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. 4239
    Prev
    Next
    INDEX
    Explanations

    explaining, describing, or considering actions

    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
    åĸĥ
    -0.07
    adero
    -0.07
     Rond
    -0.07
    æľªæĮī
    -0.07
    éĽģ
    -0.07
    ág
    -0.07
    amanan
    -0.07
    yser
    -0.07
    IgnoreCase
    -0.07
    æłĵ
    -0.07
    POSITIVE LOGITS
     modeling
    0.10
    建模
    0.10
     analysis
    0.10
     analyzing
    0.09
     treating
    0.08
     accurate
    0.08
     анализа
    0.08
    åĪĨæŀIJçļĦ
    0.08
    ç»ĺ
    0.08
     studying
    0.08
    Activations Density 0.141%

    No Known Activations