© 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. 42898
    Prev
    Next
    INDEX
    Explanations

    NEW Academy

    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
    c
    -0.06
     c
    -0.06
     d
    -0.06
    ↵↵
    -0.06
    ges
    -0.06
    ↵
    -0.06
     di
    -0.06
    éĿ¢çļĦ
    -0.06
    -0.06
     oper
    -0.06
    POSITIVE LOGITS
    uhan
    0.09
    ×ķ×ijר
    0.09
     Tro
    0.08
    .fil
    0.08
    erci
    0.08
     ТÑĢо
    0.08
     exac
    0.08
    Tro
    0.08
     ÑĤÑĢо
    0.08
    ä¸ĢåĽ¢
    0.08
    Activations Density 0.040%

    No Known Activations