© 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. 56337
    Prev
    Next
    INDEX
    Explanations

    units of measurement and prefixes

    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
    ä¸įäºĨäºĨ
    -0.07
     пÑĢоÑĪло
    -0.07
    åݿ人æ°ijæ³ķéĻ¢
    -0.07
    çªį
    -0.06
    ä¾ł
    -0.06
    ç»ıèIJ¥è®¸åı¯è¯ģ
    -0.06
     mutil
    -0.06
    大èĥĨçļĦ
    -0.06
    ertas
    -0.06
    sert
    -0.06
    POSITIVE LOGITS
    ailable
    0.08
    åľ
    0.07
    acle
    0.07
    ido
    0.07
    arp
    0.07
    èĻĶ
    0.07
    idos
    0.07
    é¶
    0.07
    èº
    0.07
    SD
    0.07
    Activations Density 0.004%

    No Known Activations