© 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. 27510
    Prev
    Next
    INDEX
    Explanations

    count, part, first

    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
    å°Ĭ
    -0.08
     Perman
    -0.08
    大åıij
    -0.08
     gebe
    -0.07
    æĮ½
    -0.07
     kÃŃnh
    -0.06
    ä¸ĢçĶŁ
    -0.06
    erings
    -0.06
     formerly
    -0.06
    aisu
    -0.06
    POSITIVE LOGITS
    -count
    0.07
     count
    0.07
     COUNT
    0.07
    ä¸įçŁ¥ä¸įè§īä¸Ń
    0.07
    çļĦ第
    0.07
    ãĤ«ãĤ¦ãĥ³ãĥĪ
    0.07
     pushed
    0.07
     Äijếm
    0.07
     Count
    0.07
     counting
    0.07
    Activations Density 0.002%

    No Known Activations