© 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. 10928
    Prev
    Next
    INDEX
    Explanations

    linux kernel include

    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
    æ´²
    -0.08
    OCR
    -0.08
    .edu
    -0.07
     ÐĵÐIJ
    -0.07
    /csv
    -0.07
     GIA
    -0.07
    ç¬ĭ
    -0.07
    èĢĥ级
    -0.07
    çIJĨèµĶ
    -0.07
    èıĩ
    -0.06
    POSITIVE LOGITS
     minst
    0.09
     OMAP
    0.08
    amba
    0.08
    omap
    0.08
     timespec
    0.08
    airo
    0.08
     omap
    0.08
    _ring
    0.07
    _linux
    0.07
     linux
    0.07
    Activations Density 0.505%

    No Known Activations