© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2863
    Prev
    Next
    INDEX
    Explanations

    company names and copyright notices

    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
    RY
    -0.07
    ãĥ³ãĥī
    -0.07
    ån
    -0.07
    äk
    -0.07
    Ầ
    -0.07
    anje
    -0.07
    Ñħай
    -0.07
    çĥŃçĤ¹æĸ°éĹ»
    -0.07
    eri
    -0.07
    tring
    -0.07
    POSITIVE LOGITS
    hoek
    0.07
    ä¹ĭå®Ŀ
    0.06
    -owned
    0.06
    åĨħèĦı
    0.06
    .com
    0.06
     evacuated
    0.06
    unno
    0.06
     LGBTQ
    0.06
    /Library
    0.06
    Transform
    0.06
    Activations Density 0.140%

    No Known Activations