© 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. 47809
    Prev
    Next
    INDEX
    Explanations

    pdf files and reader

    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
    æĢ§åľ°
    -0.09
    strup
    -0.09
    lessly
    -0.09
    FUL
    -0.09
    íĶĪ
    -0.08
    νοÏĤ
    -0.08
    ful
    -0.08
    erten
    -0.08
    fulness
    -0.08
    efore
    -0.08
    POSITIVE LOGITS
    .gz
    0.06
    rary
    0.06
    å¨ħ
    0.06
    ängel
    0.06
    /png
    0.06
    ä¸Ģè´¯
    0.06
    ä¸Ģè§ģ
    0.06
    å°¼äºļ
    0.06
    à¹ģà¸Ķà¸ĩ
    0.06
    (crate
    0.06
    Activations Density 0.048%

    No Known Activations