© 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. 40315
    Prev
    Next
    INDEX
    Explanations

    Brents, Washington, Rock, Zn

    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
    én
    -0.07
    纫
    -0.07
     unanimously
    -0.07
     Cie
    -0.06
    ä¸įäºĮ
    -0.06
    .bold
    -0.06
    aper
    -0.06
    enh
    -0.06
    aff
    -0.06
    äºĮä½į
    -0.06
    POSITIVE LOGITS
     inconsistent
    0.10
    æĺ¯éĶĻ误çļĦ
    0.09
    对æ¯Ķ
    0.09
    åıįéĿ¢
    0.09
    å¦Ħ
    0.09
    è¯ķåĽ¾
    0.09
    éĶĻ误çļĦ
    0.09
     mauvaise
    0.08
    ä¸įåħ·å¤ĩ
    0.08
     inadequate
    0.08
    Activations Density 0.206%

    No Known Activations