© 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. 44996
    Prev
    Next
    INDEX
    Explanations

    source and drain

    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
    å°ıæ¡¥
    -0.07
    AGEM
    -0.07
    -assets
    -0.07
    eteria
    -0.07
    ç¶Ļ
    -0.07
    ivamente
    -0.06
     Betten
    -0.06
    (non
    -0.06
    ä¸Ģ转
    -0.06
    bras
    -0.06
    POSITIVE LOGITS
    åĴĮ西
    0.09
     maupun
    0.09
    ãĢģ
    0.08
     lẫn
    0.08
    åĴĮåIJİ
    0.08
    åĩĨ
    0.08
    æľºåĴĮ
    0.08
    resp
    0.07
    åį¡åĴĮ
    0.07
    èIJ©
    0.07
    Activations Density 0.035%

    No Known Activations