© 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. 58290
    Prev
    Next
    INDEX
    Explanations

    "> xml closing tags

    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
    Ø©
    -0.10
    ева
    -0.07
    ↵↵
    -0.06
    ado
    -0.06
    ев
    -0.06
    eball
    -0.06
    one
    -0.06
    Ùħر
    -0.05
    اÙĨات
    -0.05
    ео
    -0.05
    POSITIVE LOGITS
    ither
    0.09
    chter
    0.08
    ÑĤаки
    0.08
    uggy
    0.08
    Injected
    0.08
    ÙĨدÙĬ
    0.08
    åħ¶ä¸ī
    0.08
    è´£ç¼ĸ
    0.08
    微信æī«ä¸Ģæī«
    0.08
    chtet
    0.07
    Activations Density 0.109%

    No Known Activations