© 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. 62717
    Prev
    Next
    INDEX
    Explanations

    variable indicating position in a sequence

    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
    ients
    -0.07
    ä½Ļ
    -0.07
    éĩıåĴĮ
    -0.07
    ä¼Ļ伴们
    -0.07
    Streamer
    -0.06
     marad
    -0.06
    ÑĢав
    -0.06
     даже
    -0.06
     nature
    -0.06
    çĶļèĩ³åľ¨
    -0.06
    POSITIVE LOGITS
    annen
    0.08
     particular
    0.08
    缴æİ¥æĪĸ
    0.07
    standen
    0.07
    éĢıå½»
    0.07
    æĪĸ以
    0.07
    å¹¢
    0.06
    丧
    0.06
    åįĥä¸ĩä¸įèĥ½
    0.06
    зÑĢа
    0.06
    Activations Density 0.019%

    No Known Activations