© 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. 46019
    Prev
    Next
    INDEX
    Explanations

    past tense verbs or completed actions

    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
    åĴĮæĸ¹æ³ķ
    -0.07
    ãĤ¹ãĤ¿
    -0.07
    entine
    -0.07
    ತà³įತà³ģ
    -0.06
    ence
    -0.06
    elum
    -0.06
    iono
    -0.06
    _INITIALIZ
    -0.06
    entrata
    -0.06
    å°ıä¼Ļ
    -0.06
    POSITIVE LOGITS
    edBy
    0.08
     singly
    0.08
    reich
    0.08
    æĨij
    0.08
     feas
    0.07
    çļ±çľī
    0.07
    /generated
    0.07
    Aj
    0.07
    åĩŃ
    0.07
    è´¹çŃī
    0.07
    Activations Density 0.014%

    No Known Activations