© 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. 29863
    Prev
    Next
    INDEX
    Explanations

    in a, in what, in this

    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
    ustralian
    -0.06
    “
    -0.06
    è¾Ļ
    -0.06
    йдеÑĤ
    -0.06
    nist
    -0.06
    ...
    -0.06
    ipher
    -0.06
    irks
    -0.06
    ÑģÑĤави
    -0.06
    å¸Ĥåľºå¯¹
    -0.06
    POSITIVE LOGITS
    oue
    0.10
     entanto
    0.08
    ;y
    0.08
    vero
    0.08
     ×ĸ×IJת
    0.08
     quoi
    0.08
    æĪijæĿ¥è¯´
    0.08
    ;x
    0.08
    èĢĮè¨Ģ
    0.08
    ä¸įäºĨçļĦ
    0.08
    Activations Density 0.901%

    No Known Activations