© 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. 2054
    Prev
    Next
    INDEX
    Explanations

    math notation or code paths

    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
    åĩīäºĨ
    -0.08
    åŃ£åĨĽ
    -0.08
    è£ĺ
    -0.07
    apiro
    -0.07
    天ä¸ĭçļĦ
    -0.07
    èĬ±èIJ½
    -0.07
    atsby
    -0.07
    łĢ
    -0.07
    YST
    -0.07
    å±±å·Ŀ
    -0.07
    POSITIVE LOGITS
    å°±æĢķ
    0.08
    èĩªæĪij
    0.07
    åį±éĻ©çļĦ
    0.07
    åį±éĻº
    0.07
    åį±æľºçļĦ
    0.07
    åį±æ©Ł
    0.06
    Ñĩив
    0.06
    çĻ¾åĪĨçĤ¹
    0.06
    _self
    0.06
     predic
    0.06
    Activations Density 0.003%

    No Known Activations