© 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. 51433
    Prev
    Next
    INDEX
    Explanations

    generally, usually, normally, typically

    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
    [image
    -0.08
    æĪijç»Īäºİ
    -0.08
    èİ«éĿŀ
    -0.08
    (Of
    -0.08
    ramework
    -0.08
    akwa
    -0.08
    kering
    -0.08
    åĪ°åºķæĺ¯ä»Ģä¹Ī
    -0.08
    ecided
    -0.08
    æį®è¯´
    -0.08
    POSITIVE LOGITS
    æĿ¥è¯´
    0.09
     sih
    0.08
    æĦıä¹īä¸Ĭ
    0.08
    æĥħæ³ģä¸ĭ
    0.08
    æĿ¥è®²
    0.07
    çļĦåģļæ³ķ
    0.07
    ister
    0.07
    itar
    0.07
    æĺ¯è¿Ļæł·
    0.07
    æĦıä¹īä¸ĬçļĦ
    0.07
    Activations Density 0.012%

    No Known Activations