© 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. 25519
    Prev
    Next
    INDEX
    Explanations

    containers and parts

    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
    åħ¨èĪ¬
    -0.07
    ież
    -0.06
    ember
    -0.06
     verge
    -0.06
    æ·ĭæ¼ĵå°½
    -0.06
    embre
    -0.06
    iful
    -0.06
    _suffix
    -0.06
    menge
    -0.06
     Pourtant
    -0.06
    POSITIVE LOGITS
    ãģ¿ãģŁãģĦãģª
    0.10
    çĬ¶çļĦ
    0.10
    å¼ıåĴĮ
    0.09
    ãģ¨åij¼ãģ°ãĤĮãĤĭ
    0.09
    å¼ıçļĦ
    0.09
    åĪĨ许
    0.09
    çĬ¶
    0.09
    å¼ıãģ®
    0.09
    ä¹ĭ称çļĦ
    0.09
    å¼ı
    0.08
    Activations Density 0.397%

    No Known Activations