© 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. 61963
    Prev
    Next
    INDEX
    Explanations

    vision, seeing, impairment

    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
    累累
    -0.08
     comigo
    -0.07
    shire
    -0.07
     vreme
    -0.07
     Äijặn
    -0.07
    jal
    -0.07
    à¹Ĩ
    -0.07
    spir
    -0.06
    缸æĢĿ
    -0.06
    iface
    -0.06
    POSITIVE LOGITS
    аÑĤелÑĮ
    0.09
    seeing
    0.09
     goggles
    0.08
     dụ
    0.08
    /he
    0.08
     impairment
    0.08
     tárg
    0.08
    ight
    0.07
    opic
    0.07
    имоÑģÑĤÑĮ
    0.07
    Activations Density 0.033%

    No Known Activations