© 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. 27401
    Prev
    Next
    INDEX
    Explanations

    pretty-printers

    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
    åĴ
    -0.08
    ä¸įè´¥
    -0.07
     Suh
    -0.07
    ä¸įæīĵ
    -0.06
     tur
    -0.06
    强
    -0.06
    ça
    -0.06
     menjan
    -0.06
    å½ĵä¹ĭ
    -0.06
    /functions
    -0.06
    POSITIVE LOGITS
    кÑĢа
    0.08
    ä¹IJä¹İ
    0.08
    ACY
    0.08
    룬ìĬ¤
    0.08
    ewn
    0.08
    èĥĮéĿł
    0.07
    Spi
    0.07
    çŃīåIJĦ项
    0.07
    esy
    0.07
    iez
    0.07
    Activations Density 0.033%

    No Known Activations