© 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. 63993
    Prev
    Next
    INDEX
    Explanations

    numbers, units, and dates

    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
    haj
    -0.07
    ä¸įåĬ¨
    -0.07
    ingat
    -0.07
    utow
    -0.07
    yster
    -0.07
    _PAYLOAD
    -0.06
    éĺ¶çº§çļĦ
    -0.06
    ingo
    -0.06
    loo
    -0.06
    åĪĺ家
    -0.06
    POSITIVE LOGITS
    elan
    0.08
    ivre
    0.07
    大峡谷
    0.07
     mieh
    0.07
    ä¸įèĭŁ
    0.07
    ibre
    0.07
    央è§Ĩç½ij
    0.07
    ittle
    0.07
    cite
    0.07
    ereo
    0.07
    Activations Density 0.002%

    No Known Activations