© 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. 28526
    Prev
    Next
    INDEX
    Explanations

    implicit object

    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
    1
    -0.06
     "
    -0.05
    åĪĺ家
    -0.05
     Maha
    -0.05
     pp
    -0.05
     Deep
    -0.05
    çļĦä¸Ģå¹´éĩĮ
    -0.05
    Âł
    -0.05
    VC
    -0.05
    rah
    -0.05
    POSITIVE LOGITS
    porti
    0.08
    缸åıį
    0.08
    èĩ³äºİ
    0.08
    פ×ĺ
    0.08
    setState
    0.08
    èĩ³æĸ¼
    0.08
    поÑĢÑĤа
    0.08
    麼
    0.08
    gnore
    0.08
     **¡
    0.08
    Activations Density 0.015%

    No Known Activations