© 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. 20958
    Prev
    Next
    INDEX
    Explanations

    file path components

    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
    nÃŃ
    -0.06
    ievo
    -0.06
    /sites
    -0.06
    {}",
    -0.06
     =
    -0.06
     âĤ¬,
    -0.06
    ie
    -0.06
    2
    -0.06
    YN
    -0.05
    aka
    -0.05
    POSITIVE LOGITS
    çļĦåIJĹ
    0.12
    éĹ®é¢ĺäºĨ
    0.12
    ä¸Ģæł·äºĨ
    0.10
    >>()
    0.10
    ä¸įåIJĮäºĨ
    0.10
    çļĦäºĨ
    0.10
    çļĦæŶåĢĻäºĨ
    0.10
    äºĨåIJĹ
    0.09
    >()
    0.09
    åIJĪåIJĮæŶ
    0.09
    Activations Density 0.674%

    No Known Activations