© 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. 16207
    Prev
    Next
    INDEX
    Explanations

    day delivery, new species, airport operations

    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
    çīŁ
    -0.08
    encent
    -0.07
    çĪ±ä¸įéĩĬ
    -0.07
    ä¹°ä¹°
    -0.07
    ISTIC
    -0.07
    èĨĺ
    -0.07
     mono
    -0.07
    èıģ
    -0.07
    ĻĤ
    -0.06
    æīĵèµ·
    -0.06
    POSITIVE LOGITS
    æĿ¯ä¸Ń
    0.07
    çŁ¥
    0.07
    åı¥è¯Ŀ
    0.07
    åĢ¦
    0.07
    æĢĿ
    0.07
    ÛĮس
    0.07
    èĢĮçŁ¥
    0.07
    åħ¨éĻ¢
    0.07
    éª
    0.06
     Optim
    0.06
    Activations Density 0.019%

    No Known Activations