© 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. 13221
    Prev
    Next
    INDEX
    Explanations

    making choices or decisions

    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
    뢰
    -0.07
    umbo
    -0.07
    èŁĨ
    -0.07
    èİĺ
    -0.07
    æĮĩçļĦ
    -0.06
     buit
    -0.06
    ÑİÑĢи
    -0.06
    åĪĨæł¡
    -0.06
    ToObject
    -0.06
    ria
    -0.06
    POSITIVE LOGITS
    èĩªçĶ±éĢīæĭ©
    0.16
     freely
    0.16
    èĩªä¸»éĢīæĭ©
    0.14
    èĩªçĶ±
    0.14
    èĩªçĶ±çļĦ
    0.13
    åĨ³å®ļæĺ¯åIJ¦
    0.13
    èĩªä¸»
    0.13
    èĩªçĶ±ãģ«
    0.12
    æł¹æį®èĩªå·±çļĦ
    0.12
    æĿ¥åĨ³å®ļ
    0.11
    Activations Density 0.126%

    No Known Activations