© 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. 15109
    Prev
    Next
    INDEX
    Explanations

    restore point, refresh, encryption, capture, insertion unit

    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
    åıijå±ķåĴĮ
    -0.10
    åıĺåĮĸåĴĮ
    -0.09
    åĪĨæŀIJä¸İ
    -0.09
    å¼ĢåıijåĴĮ
    -0.09
    å®£ä¼łåĴĮ
    -0.09
    使çĶ¨åĴĮ
    -0.09
    éĢīæĭ©åĴĮ
    -0.09
    åĪĨæŀIJåĴĮ
    -0.08
    ernen
    -0.08
    次çļĦ
    -0.08
    POSITIVE LOGITS
    èĢħ
    0.13
    èĢħçļĦ
    0.12
    å·²ä¹ħçļĦ
    0.09
    able
    0.09
    èĢħåĴĮ
    0.09
    åĻ¨
    0.09
    çĿĢçļĦ
    0.09
    è¿ĩçļĦ
    0.09
    ä¸įäºĨ
    0.09
    æĸ¹å¼ı
    0.09
    Activations Density 0.023%

    No Known Activations