© 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. 62928
    Prev
    Next
    INDEX
    Explanations

    defining variables with let

    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
    بخ
    -0.08
    emas
    -0.07
    è¤Ĵ
    -0.07
    ople
    -0.07
    irme
    -0.07
    Zimmer
    -0.07
    inna
    -0.07
    agio
    -0.07
     íĩ´
    -0.06
    oteric
    -0.06
    POSITIVE LOGITS
    éĹ®é¢ĺåĪĨæŀIJ
    0.08
    é¦ĸåħĪ
    0.07
    ibold
    0.07
    üz
    0.07
    ĥģ
    0.06
     Brewer
    0.06
     ìĿ¼ëĭ¨
    0.06
    æľ¬å¸ĸ
    0.06
    emi
    0.06
    èŁĭ
    0.06
    Activations Density 0.005%

    No Known Activations