© 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. 27990
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and variables

    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
    åĴĮæĮijæĪĺ
    -0.07
    a
    -0.07
     discrete
    -0.06
    ç»ıæµİå½¢åĬ¿
    -0.06
     minus
    -0.06
    è¿Ļ个æĹ¶ä»£
    -0.06
     Weiner
    -0.06
    imia
    -0.06
    åĨįè¿ĩ
    -0.06
     halfway
    -0.05
    POSITIVE LOGITS
    pga
    0.09
    azu
    0.09
    ATEN
    0.08
    occ
    0.08
    ptrdiff
    0.08
    aknya
    0.08
    Deg
    0.08
    vox
    0.08
    adena
    0.08
    egrad
    0.08
    Activations Density 0.010%

    No Known Activations