© 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. 16294
    Prev
    Next
    INDEX
    Explanations

    "is" or "are" followed by phrase

    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
    é¢ĸ
    -0.07
    éł»
    -0.06
    ç©İ
    -0.06
    æŁĶ
    -0.06
    è¶Ĭåıij
    -0.06
    iap
    -0.06
    plos
    -0.06
    usting
    -0.06
    çºĸ
    -0.06
    asket
    -0.06
    POSITIVE LOGITS
    ä¸įå¾Ĺ以任ä½ķ
    0.08
    former
    0.08
    coni
    0.08
    为åħĪ
    0.08
    tere
    0.08
    æľĪåĦ¿
    0.08
    ingi
    0.08
     asa
    0.07
    ked
    0.07
    西åĵ¥
    0.07
    Activations Density 0.009%

    No Known Activations