© 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. 42019
    Prev
    Next
    INDEX
    Explanations

    ancers build

    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
    ein
    -0.07
    çİīå±±
    -0.07
    åĪĨ享ç»Ļ大家
    -0.07
    e
    -0.07
    åĨħç»ı
    -0.06
    short
    -0.06
    ãģĿãĤĮãĤĴ
    -0.06
    ÑĩÑijÑĤ
    -0.06
    å±ķé¦Ĩ
    -0.06
    ysz
    -0.06
    POSITIVE LOGITS
    éĺħè¯»æľ¬æĸĩåīį
    0.09
    å·²ç»ıå°Ĩ
    0.08
    继ç»Ńåľ¨
    0.08
    ç»ıæµİåѦéĻ¢
    0.07
    çĦķçĦ¶
    0.07
    è¿Ŀåıįä¸Ĭè¿°
    0.07
    éĻ¤äºĨè¦ģ
    0.07
    itera
    0.07
    AsyncResult
    0.07
    åľ¨è¿Ļ次
    0.07
    Activations Density 0.007%

    No Known Activations