© 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. 48304
    Prev
    Next
    INDEX
    Explanations

    sequence alignment and parsing

    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
    社ä¼ļåıijå±ķ
    -0.08
    -validator
    -0.07
    åįģæĿ¡
    -0.07
    기ìĤ¬
    -0.07
    ovah
    -0.07
    ereg
    -0.07
    лок
    -0.07
    çİ®
    -0.07
    åĴĮ社ä¼ļåıijå±ķ
    -0.07
    æŃ¤æ¬¾
    -0.06
    POSITIVE LOGITS
     preprocess
    0.08
    åĴĮåĪĨæŀIJ
    0.08
    å½±éŁ³
    0.08
     preprocessing
    0.08
     préalable
    0.07
    yto
    0.07
    å¸ĸ
    0.07
    SetUp
    0.07
    天åı°
    0.07
    ardu
    0.07
    Activations Density 0.073%

    No Known Activations