© 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. 29029
    Prev
    Next
    INDEX
    Explanations

    history of

    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
    两个æľĪ
    -0.08
    æĹĭåį³
    -0.07
    äºĶæĹ¥
    -0.07
    åij¼å£°
    -0.07
    رÙĥ
    -0.07
    çŃīæĸ°
    -0.07
    天ä»Ļ
    -0.07
     недел
    -0.07
     imminent
    -0.07
    ä¸Ģ个å¤ļæľĪ
    -0.07
    POSITIVE LOGITS
     history
    0.20
     History
    0.17
    åİĨåı²ä¸ĬçļĦ
    0.17
    history
    0.17
    åİĨåı²çļĦ
    0.16
    åİĨåı²
    0.16
    åİĨä»»
    0.15
    History
    0.15
     historical
    0.15
    -history
    0.15
    Activations Density 0.571%

    No Known Activations