© 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. 48910
    Prev
    Next
    INDEX
    Explanations

    code main functions

    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
    iez
    -0.07
    apol
    -0.07
    eni
    -0.07
    人为
    -0.06
    ocks
    -0.06
    ooks
    -0.06
    ì·¨
    -0.06
    æĺ¯å¤§
    -0.06
     tele
    -0.06
    memberOf
    -0.06
    POSITIVE LOGITS
    iams
    0.08
    lobals
    0.08
    åĴķ
    0.08
    wiss
    0.07
    å°¼äºļ
    0.07
    egis
    0.07
    尼奥
    0.07
    illot
    0.07
     maiden
    0.07
     calls
    0.07
    Activations Density 0.001%

    No Known Activations