© 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. 48311
    Prev
    Next
    INDEX
    Explanations

    relativistic speed surge

    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
    éĿ¢ç§¯çļĦ
    -0.08
    Ø«ÙĪر
    -0.07
    汶
    -0.07
    éĿ¢ç§¯ä¸º
    -0.07
    aire
    -0.07
    inha
    -0.07
    oare
    -0.07
    egel
    -0.06
    æµ·å²Ľ
    -0.06
     basis
    -0.06
    POSITIVE LOGITS
    stream
    0.08
    çĬ¶æħĭãģ§
    0.07
    statuses
    0.07
     strm
    0.07
    æİ¥è¿ij
    0.07
     boosting
    0.07
    å°Ķå¤ļ
    0.07
    state
    0.07
    edan
    0.07
    æµģåħī
    0.07
    Activations Density 0.002%

    No Known Activations