© 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. 14547
    Prev
    Next
    INDEX
    Explanations

    variables and numeric expressions

    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
    tron
    -0.06
    ä¸Ĭä¸Ģå±Ĥ
    -0.06
    åľĪ
    -0.06
    Mui
    -0.06
    uel
    -0.06
     parted
    -0.06
    utor
    -0.06
    äºĨä¸Ģå±Ĥ
    -0.06
    éļı
    -0.06
    -l
    -0.06
    POSITIVE LOGITS
    conomic
    0.08
    交æīĢ
    0.08
     Econom
    0.08
     Seger
    0.08
    çĪ±ä¸įéĩĬæīĭ
    0.08
     Economic
    0.08
    åĽ¾çīĩæĿ¥æºIJäºİç½ij绾
    0.08
     economic
    0.07
    ecimal
    0.07
    æľ¬é¡µ
    0.07
    Activations Density 0.004%

    No Known Activations