© 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. 13331
    Prev
    Next
    INDEX
    Explanations

    sequence fragments or copies

    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
    osu
    -0.08
     RGBA
    -0.07
    à¹īà¸ĩ
    -0.07
    Eu
    -0.07
    湿
    -0.07
    icter
    -0.06
    渣
    -0.06
     décol
    -0.06
    第äºĮç±»
    -0.06
     пÑĥлÑĮ
    -0.06
    POSITIVE LOGITS
     fragment
    0.10
     fragments
    0.09
    å®Įæķ´åľ°
    0.09
     cassette
    0.09
    两段
    0.09
    concat
    0.09
     ÑĦÑĢаг
    0.09
    åµĮåħ¥
    0.08
    æıĴåħ¥
    0.08
    çļĦç»ĵæŀĦ
    0.08
    Activations Density 0.085%

    No Known Activations