© 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. 23075
    Prev
    Next
    INDEX
    Explanations

    Ant. characters

    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
    强
    -0.08
    inema
    -0.07
    ä¸ĢæľĿ
    -0.07
    çİĦå¾·
    -0.07
    便被
    -0.07
    elv
    -0.07
    inth
    -0.07
    Clipboard
    -0.06
    oya
    -0.06
    æĶ¿
    -0.06
    POSITIVE LOGITS
    å¾·ç½Ĺ
    0.08
    ضÙĬع
    0.07
    éļIJ
    0.07
    åķ¼
    0.07
    åIJīæĸ¯
    0.07
    typ
    0.06
    past
    0.06
    å¸ĥæĸ¯
    0.06
    ÙĩÙĨ
    0.06
    ossi
    0.06
    Activations Density 0.066%

    No Known Activations