© 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. 31171
    Prev
    Next
    INDEX
    Explanations

    randomized trials

    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
    azzi
    -0.07
     многое
    -0.07
     vs
    -0.06
    T
    -0.06
    åıĪè¦ģ
    -0.06
     wed
    -0.06
    æĺĵ
    -0.06
     ÃŃgy
    -0.06
    rani
    -0.06
    alem
    -0.06
    POSITIVE LOGITS
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    0.09
    دÙģ
    0.07
    漩
    0.07
    isit
    0.07
    æľīå¤ļä¹Ī
    0.07
    imu
    0.07
    æīĢå±ŀåĪĨç±»
    0.07
     vorba
    0.07
    .dy
    0.07
    venta
    0.07
    Activations Density 0.071%

    No Known Activations