© 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. 29744
    Prev
    Next
    INDEX
    Explanations

    meta descriptions, object, services

    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
    geois
    -0.08
    zinho
    -0.08
    aging
    -0.08
    jenigen
    -0.08
    迪äºļ
    -0.08
     ëĤĺìĦľ
    -0.08
    iness
    -0.07
     overe
    -0.07
    evity
    -0.07
    liness
    -0.07
    POSITIVE LOGITS
    ثر
    0.08
    ãģıãģ¡ãĤĥ
    0.08
    ÙĪسطة
    0.08
    ropolitan
    0.08
    خذ
    0.08
    ussin
    0.07
    åĶij
    0.07
    ç¥Ŀ大家
    0.07
    weet
    0.07
    ysical
    0.07
    Activations Density 0.086%

    No Known Activations