© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25927
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

    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
    sic
    -0.08
    езде
    -0.08
    æĽ´å¤ļä¿¡æģ¯
    -0.07
    ä¸įçĶ¨è¯´
    -0.07
    她表示
    -0.07
    езда
    -0.06
     vả
    -0.06
    sch
    -0.06
    ewnÄħ
    -0.06
    info
    -0.06
    POSITIVE LOGITS
    en
    0.08
    åŃļ
    0.08
    alj
    0.07
    Ø©
    0.07
    led
    0.07
    zÃŃ
    0.07
    antly
    0.07
    lessly
    0.07
    icie
    0.07
    и
    0.07
    Activations Density 0.068%

    No Known Activations