© 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. 29317
    Prev
    Next
    INDEX
    Explanations

    its own file or line

    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
    æIJŃ
    -0.07
    æĺ¯ä¸Ģç§įéĿŀ常
    -0.07
    ysi
    -0.07
    ockets
    -0.07
    大éĥ¨ä»½
    -0.07
    ÄĻt
    -0.07
    ikus
    -0.07
    igers
    -0.07
    çĤ¹æķ°
    -0.06
     Mog
    -0.06
    POSITIVE LOGITS
    ç´§æİ¥çĿĢ
    0.08
    ugi
    0.08
     dedicated
    0.07
    å±±éķĩ
    0.07
    è¦ģä¹Ī
    0.07
     Dedicated
    0.07
    åħĪæĺ¯
    0.07
    wend
    0.06
    米线
    0.06
    pread
    0.06
    Activations Density 0.002%

    No Known Activations