© 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. 55958
    Prev
    Next
    INDEX
    Explanations

    flower, flowers, flowered

    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
    äºĨ
    -0.07
     اÙĦذاتÙĬØ©
    -0.06
    oire
    -0.06
    емÑĥ
    -0.06
    oodles
    -0.06
    ellem
    -0.06
    alak
    -0.06
    elight
    -0.06
     веÑīей
    -0.06
    ption
    -0.06
    POSITIVE LOGITS
    ä¸įè´¥
    0.09
    丼
    0.09
    ç°ĩ
    0.09
    èķĬ
    0.09
    åĽĽæº¢
    0.09
    eries
    0.08
    èĬĤçļĦ
    0.08
    lover
    0.08
    åİĤçļĦ
    0.08
    å¾Īç¾İ
    0.08
    Activations Density 0.039%

    No Known Activations