© 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. 62382
    Prev
    Next
    INDEX
    Explanations

    drug substances

    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
    è¿«
    -0.07
    uced
    -0.07
    cza
    -0.06
    ivs
    -0.06
     repris
    -0.06
     Grat
    -0.06
    çĶ±æѤ
    -0.06
    çĽ¾
    -0.06
    avu
    -0.06
    èĢ»
    -0.06
    POSITIVE LOGITS
    olio
    0.08
    ä¸ĭåIJĮ
    0.08
    å¹¼ç¨ļ
    0.08
    çijĻ
    0.07
    æĪIJçĨŁäºĨ
    0.07
    знÑı
    0.07
    previous
    0.07
     appunto
    0.07
    Öģ
    0.07
    ADX
    0.07
    Activations Density 0.273%

    No Known Activations