© 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. 64427
    Prev
    Next
    INDEX
    Explanations

    reading lines from input or files

    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
    filesize
    -0.07
    jsc
    -0.07
    olim
    -0.07
    èIJ¥éĢłä¸Ģ个
    -0.07
    -beta
    -0.07
    raction
    -0.07
    xel
    -0.07
    OOK
    -0.07
    æijĬ
    -0.07
    TRL
    -0.07
    POSITIVE LOGITS
    縱
    0.07
    并ç»Ħç»ĩ
    0.07
    à¸Ĺาย
    0.07
    enda
    0.07
    äºĭæĪIJ
    0.06
    è¡
    0.06
    ุย
    0.06
    ãĪ
    0.06
    æĶ¿
    0.06
    gar
    0.06
    Activations Density 0.001%

    No Known Activations