© 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. 33680
    Prev
    Next
    INDEX
    Explanations

    mathematics and programming constructs

    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
    ures
    -0.07
    mert
    -0.07
    åIJĮä¸Ģ个
    -0.07
    éļı便
    -0.07
    uren
    -0.06
    hof
    -0.06
    kan
    -0.06
     depress
    -0.06
    æ¯Ķè¾ĥå°ij
    -0.06
    gun
    -0.06
    POSITIVE LOGITS
    å·¥ç¨ĭ设计
    0.07
    éģ¥
    0.07
     Marvin
    0.07
    ardım
    0.07
    bens
    0.07
    пиÑĤа
    0.07
    далее
    0.07
    åIJĿ
    0.07
    Recognizer
    0.07
    sonian
    0.07
    Activations Density 0.001%

    No Known Activations