© 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. 64512
    Prev
    Next
    INDEX
    Explanations

    German names and entities

    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
    åĴĮ群ä¼Ĺ
    -0.07
    åĮĸåĴĮ
    -0.07
    åĴĮçłĶ究
    -0.07
    åĴĮèµĦæºIJ
    -0.07
    åĴĮ管çIJĨ
    -0.07
    åħ·
    -0.07
    coa
    -0.06
    _NONE
    -0.06
    otte
    -0.06
    åĴĮ社åĮº
    -0.06
    POSITIVE LOGITS
     respectively
    0.19
     alike
    0.17
    åīįèĢħ
    0.14
    åĪĨåĪ«
    0.13
    ãģĿãĤĮãģŀãĤĮ
    0.13
     jeweils
    0.12
    åIJĦèĩªçļĦ
    0.12
    åĪĨåĪ«ä»İ
    0.12
    è¿Ļ两个
    0.12
     respectiv
    0.12
    Activations Density 0.686%

    No Known Activations