© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 8981
    Prev
    Next
    INDEX
    Explanations

    information is important

    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
    ìĦŃ
    -0.07
    ukt
    -0.07
    eko
    -0.07
    ÙİÙijÙĩÙı
    -0.07
    кеÑĢ
    -0.07
    вно
    -0.07
    adar
    -0.07
    ä¸įèµ·
    -0.07
    аÑĤÑĥÑĢ
    -0.06
    onas
    -0.06
    POSITIVE LOGITS
    è¿Ļ对äºİ
    0.17
    è¿Ļ对
    0.15
    缴æİ¥åħ³ç³»åĪ°
    0.15
    åħ³ç³»åĪ°
    0.14
    åħ·æľīéĩįè¦ģçļĦ
    0.13
    æľīçĽĬäºİ
    0.13
     important
    0.13
    æľīåĬ©äºİ
    0.12
    éĩįè¦ģçļĦ
    0.12
    缮çļĦæĺ¯ä¸ºäºĨ
    0.12
    Activations Density 1.074%

    No Known Activations