© 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. 2812
    Prev
    Next
    INDEX
    Explanations

    focus is / on / has

    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
    ibas
    -0.08
     dicip
    -0.07
    hood
    -0.07
    ìĨĶ
    -0.07
    åıĤä¸İäºĨ
    -0.07
    uber
    -0.07
    ytu
    -0.07
    æĥħåĨµè¯´æĺİ
    -0.07
    วาà¸Ļ
    -0.07
     sy
    -0.06
    POSITIVE LOGITS
     focus
    0.22
     focuses
    0.18
    focus
    0.17
     Focus
    0.17
    Focus
    0.17
    çĦ¦çĤ¹
    0.16
     focusing
    0.16
    _focus
    0.16
     focused
    0.15
    èģļçĦ¦
    0.15
    Activations Density 0.136%

    No Known Activations