© 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. 16446
    Prev
    Next
    INDEX
    Explanations

    positive real semi-axis

    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
    ä¸İç»´ä¿®
    -0.07
    arcy
    -0.07
     limburg
    -0.07
    .assertAlmostEqual
    -0.07
    verages
    -0.07
    linger
    -0.07
    petto
    -0.07
     vandal
    -0.07
    åĵĪåĪ©æ³¢çī¹
    -0.07
    @example
    -0.07
    POSITIVE LOGITS
    èĦIJ
    0.08
     boyunca
    0.07
    credi
    0.07
    干线
    0.07
    æĺ¯ä¸ĢæĿ¡
    0.07
    åIJīå®ī
    0.07
    延伸èĩ³
    0.06
    ÙĬÙĦØ©
    0.06
    èĤĿ
    0.06
    æ·±
    0.06
    Activations Density 0.003%

    No Known Activations