© 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. 42699
    Prev
    Next
    INDEX
    Explanations

    shallow waters

    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
    ква
    -0.09
     ÐłÐ°ÑģÑģка
    -0.08
    igli
    -0.08
    igan
    -0.08
    ogne
    -0.08
    umph
    -0.08
    anzas
    -0.08
    ding
    -0.08
    yled
    -0.08
     thầm
    -0.08
    POSITIVE LOGITS
    ly
    0.12
    층
    0.09
    æµħ
    0.09
    æ·º
    0.09
    èĸĦçļĦ
    0.09
     layer
    0.08
     shallow
    0.08
    à¹Ĩ
    0.08
     sekali
    0.08
    å±ĤçļĦ
    0.08
    Activations Density 0.016%

    No Known Activations