© 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. 11344
    Prev
    Next
    INDEX
    Explanations

    research, studies, and data analysis

    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
    以èĩ³äºİ
    -0.08
     accordingly
    -0.08
    idel
    -0.07
    以èĩ³
    -0.07
    acional
    -0.07
    åĪ©
    -0.07
    ovo
    -0.07
    æĩIJ
    -0.06
    voj
    -0.06
    ׼×Ķ
    -0.06
    POSITIVE LOGITS
    ä¸ĭåIJĮ
    0.07
    zeniem
    0.07
    fcn
    0.07
    odaw
    0.07
    elage
    0.07
    èĬ±ä¸Ģ
    0.07
    å§Ĺ
    0.06
    dden
    0.06
    resta
    0.06
    blink
    0.06
    Activations Density 0.157%

    No Known Activations