© 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. 33019
    Prev
    Next
    INDEX
    Explanations

    citation markers like [@B0X]

    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
    enu
    -0.07
    _EXISTS
    -0.07
    ungan
    -0.07
    erala
    -0.07
    æľīæѤ
    -0.06
     Romania
    -0.06
    nam
    -0.06
    ноп
    -0.06
    æķ°åIJį
    -0.06
    ilo
    -0.06
    POSITIVE LOGITS
    æĸĩæijĺ
    0.08
    CKER
    0.08
    oriented
    0.08
     emer
    0.07
    ÙĪاع
    0.07
    cker
    0.07
    ãģĦãģ£ãģ±
    0.07
    ÙĪÙij
    0.07
    zd
    0.07
    ulist
    0.07
    Activations Density 0.079%

    No Known Activations