© 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. 24627
    Prev
    Next
    INDEX
    Explanations

    particle beam radiation therapy

    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
    istrator
    -0.07
    æĢ§åıĬ
    -0.06
    andang
    -0.06
    izen
    -0.06
    åĸ
    -0.06
     pou
    -0.06
     pare
    -0.06
    .decor
    -0.06
     Mog
    -0.05
    åİŁåĽł
    -0.05
    POSITIVE LOGITS
    æĪIJè´¥
    0.12
    ãģ«ãģĬãģĦãģ¦
    0.09
    ä¸ŃçļĦä½ľçĶ¨
    0.09
     wherein
    0.09
     où
    0.08
    åIJİæľŁçļĦ
    0.08
    çĶ¨åĪ°çļĦ
    0.08
    èµĸ以
    0.08
    prs
    0.08
    ä¸ŃçļĦéĩįè¦ģ
    0.08
    Activations Density 0.320%

    No Known Activations