© 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. 61569
    Prev
    Next
    INDEX
    Explanations

    site categories

    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
    ompiler
    -0.10
    _CLASSES
    -0.09
    çĶŁæ°´
    -0.09
    åħįè´¹åıijå¸ĥ
    -0.09
    oader
    -0.09
    ì¡°íļĮ
    -0.09
    ataloader
    -0.09
    é»Ħ页
    -0.08
    /bower
    -0.08
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.08
    POSITIVE LOGITS
    yf
    0.06
    ä¸ĬéĿ¢
    0.06
    aar
    0.06
     above
    0.06
     content
    0.06
    ï¼ļ
    0.06
     context
    0.06
    a
    0.05
    []
    0.05
    羿
    0.05
    Activations Density 0.379%

    No Known Activations