© 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. 11698
    Prev
    Next
    INDEX
    Explanations

    punctuation or delimiters

    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
    ä¹İ
    -0.08
    æ¶ħ
    -0.07
    å¾ĹåIJį
    -0.07
    éĴ¦
    -0.06
    ible
    -0.06
      ↵    ↵
    -0.06
    ìĭĿ
    -0.06
     daÃŃ
    -0.06
    ìĭĿìĿĺ
    -0.06
    ta
    -0.06
    POSITIVE LOGITS
    omor
    0.10
    ationToken
    0.08
    asString
    0.08
    дем
    0.07
    æķĻäºİ
    0.07
    å¼ĢåĪ°
    0.07
    aminer
    0.07
    alker
    0.07
    atelj
    0.07
    omás
    0.07
    Activations Density 0.003%

    No Known Activations