© 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. 19971
    Prev
    Next
    INDEX
    Explanations

    Sharpe, prevButton, Spam, Hello, Brief, food, .google

    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
    +
    -0.06
     con
    -0.06
    çIJī
    -0.06
    æĪ·
    -0.06
    ach
    -0.06
    ado
    -0.06
    ocom
    -0.06
    åĶĩ
    -0.06
    åºIJ
    -0.06
    æ°´ä¸Ĭ
    -0.06
    POSITIVE LOGITS
    åľ¨ä¸Ĭè¿°
    0.09
    æĿijæĿijæ°ij
    0.08
    chten
    0.08
     tadi
    0.08
    æ¯ıä¸ĢåIJį
    0.08
    ç½ijç«Ļåľ°åĽ¾
    0.08
    bove
    0.08
    ucie
    0.08
    åıĪå¦Ĥ
    0.08
    _epi
    0.08
    Activations Density 0.083%

    No Known Activations