© 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. 48653
    Prev
    Next
    INDEX
    Explanations

    possessive endings or verbs following entities

    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
    è¨
    -0.08
    ifferent
    -0.08
     echoed
    -0.08
    oub
    -0.07
    ÑģÑĤвом
    -0.07
    edback
    -0.07
    à¸ģัà¸Ļà¹ĥà¸Ļ
    -0.07
    ToDate
    -0.07
    åįĬåĬŁ
    -0.07
    à¸ģัà¸Ļ
    -0.07
    POSITIVE LOGITS
    's
    0.09
    èĩªèº«
    0.09
    èĩªèº«çļĦ
    0.08
    ’s
    0.08
    èµĸ以
    0.07
    æѤæŶçļĦ
    0.07
    å°Ĩèĩªå·±çļĦ
    0.07
    æľ¬èº«çļĦ
    0.06
    æŃ¤ä¸¾
    0.06
     vs
    0.06
    Activations Density 0.010%

    No Known Activations