© 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. 48632
    Prev
    Next
    INDEX
    Explanations

    spatial prepositions followed by 'the'

    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
    uÃŃ
    -0.09
    icke
    -0.08
    weiler
    -0.08
    æľ¬ç«ĻåĨħ容
    -0.08
    esel
    -0.08
    åįĹåĽ½
    -0.08
    ì¡´
    -0.08
    西åĮº
    -0.07
    rames
    -0.07
    edas
    -0.07
    POSITIVE LOGITS
    neath
    0.09
    /at
    0.08
     immédi
    0.07
     the
    0.07
    /in
    0.07
    /by
    0.07
    à¹Ĩ
    0.07
    ilet
    0.07
    ä¹ĭåıĪ
    0.07
     Ùħباشرة
    0.07
    Activations Density 0.278%

    No Known Activations