© 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. 50857
    Prev
    Next
    INDEX
    Explanations

    repeated actions or sequences

    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
    suppress
    -0.07
     Final
    -0.07
    æľīç¦ı
    -0.07
    каÑĥ
    -0.06
    æµ·åıĤ
    -0.06
    CEE
    -0.06
     Gì
    -0.06
    here
    -0.06
     att
    -0.06
    å¿
    -0.06
    POSITIVE LOGITS
    åĴĮ第äºĮ
    0.08
    AndUpdate
    0.08
    åĨįéĢł
    0.07
    第äºĮåIJį
    0.07
    uncul
    0.07
    fur
    0.07
    第äºĮ
    0.07
    ä¸ĭä¸Ģ级
    0.07
     segundo
    0.07
     similarly
    0.07
    Activations Density 0.023%

    No Known Activations