© 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. 48994
    Prev
    Next
    INDEX
    Explanations

    declaration completion

    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
    äºĴ帮
    -0.08
    çĽ¸çŁ¥
    -0.07
    çİĭ大
    -0.07
    åľ¨åģļ好
    -0.07
    ä½łè¿Ļä¹Ī
    -0.07
    gee
    -0.07
     Davies
    -0.07
    ÑĦа
    -0.07
    称åij¼
    -0.07
    eht
    -0.07
    POSITIVE LOGITS
    DefaultValue
    0.08
    มห
    0.08
     defaultValue
    0.07
    åĨ»
    0.07
    æķ´
    0.07
     astr
    0.06
     value
    0.06
    çļĦåĢ¼
    0.06
     zev
    0.06
     fieldValue
    0.06
    Activations Density 0.088%

    No Known Activations