© 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. 15505
    Prev
    Next
    INDEX
    Explanations

    past participles follow auxiliary verbs

    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
    åĥıä½ł
    -0.10
    fører
    -0.09
     itib
    -0.09
    羣æŃ£åľ°
    -0.08
    utenberg
    -0.08
    æĽ´å¤ļåħ³äºİ
    -0.08
    å®ĺå¾®
    -0.08
     interag
    -0.08
    ients
    -0.08
    ä¹ĭåĪĨ
    -0.08
    POSITIVE LOGITS
     grate
    0.07
     led
    0.07
    `
    0.07
    igh
    0.07
    åĢ¼å¾Ĺ
    0.06
    令人
    0.06
     ebenfalls
    0.06
     greatly
    0.06
     highlighted
    0.06
    以åıĬ对
    0.06
    Activations Density 0.761%

    No Known Activations