© 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. 58032
    Prev
    Next
    INDEX
    Explanations

    language names and countries

    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
    irt
    -0.09
    astia
    -0.08
      ↵  ↵
    -0.08
    æĿŀ
    -0.08
    éĻħ
    -0.07
    èµ
    -0.07
      č↵
    -0.07
    å¸ĸ
    -0.07
    âĢ¦and
    -0.07
    âĢ¦but
    -0.07
    POSITIVE LOGITS
    强åĬĽ
    0.07
    urray
    0.07
    yday
    0.07
    ´
    0.07
     arch
    0.06
    inheritDoc
    0.06
    å°ıç¼ĸ
    0.06
    ä»°
    0.06
    综åIJĪçĹĩ
    0.06
    大ä¸ļ
    0.06
    Activations Density 0.070%

    No Known Activations