© 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. 4247
    Prev
    Next
    INDEX
    Explanations

    John 2017

    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
    otta
    -0.07
    çī§
    -0.06
    å
    -0.06
    墨
    -0.06
    hel
    -0.06
    à¸ļา
    -0.06
    bsd
    -0.06
    brief
    -0.06
     UMA
    -0.06
    裸
    -0.06
    POSITIVE LOGITS
    usto
    0.08
    .conf
    0.07
    cito
    0.07
    以å¤ĸçļĦ
    0.07
    å®ī好
    0.07
    anat
    0.07
    ä¸Ģå®ļä¸įè¦ģ
    0.07
    icca
    0.07
    cios
    0.07
    dbo
    0.07
    Activations Density 0.272%

    No Known Activations