© 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. 48588
    Prev
    Next
    INDEX
    Explanations

    sequences involving numbers

    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
    iteli
    -0.07
    aur
    -0.07
    æĹ·
    -0.07
    PerPixel
    -0.07
    Ø´ÙĨ
    -0.07
    ailer
    -0.07
    Ïĥία
    -0.07
    atos
    -0.07
    强度é«ĺ
    -0.07
    赤峰
    -0.07
    POSITIVE LOGITS
     successive
    0.08
    æ¯ıä¸Ģ次
    0.08
    rast
    0.07
     partial
    0.07
    ä¸įæĸŃè¿ĽæŃ¥
    0.07
    ä¸Ģ次次
    0.07
    åģľåľ¨
    0.07
    æĶ¶æ¬¾
    0.07
    æ¯ı次
    0.07
    éĢ¼è¿ij
    0.06
    Activations Density 0.004%

    No Known Activations