© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26824
    Prev
    Next
    INDEX
    Explanations

    function definitions with variables

    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
    nger
    -0.07
    icc
    -0.07
    )$/
    -0.06
    ê¶ģ
    -0.06
    IDA
    -0.06
    inde
    -0.06
    åķ¼
    -0.06
     goodness
    -0.06
    bjerg
    -0.06
    天åŃIJ
    -0.06
    POSITIVE LOGITS
    á»IJI
    0.08
    صÙĬد
    0.08
    æıIJé«ĺå·¥ä½ľæķĪçİĩ
    0.07
    OTES
    0.07
    ivic
    0.07
    éĩıåĬĽ
    0.07
    anças
    0.07
    å²ij
    0.07
    astle
    0.07
    æľī太å¤ļ
    0.07
    Activations Density 0.024%

    No Known Activations