© 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. 12002
    Prev
    Next
    INDEX
    Explanations

    .us, .com, numbers

    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
    åĦ¿
    -0.07
    ka
    -0.07
    èĩªçĶ±æ´»åĬ¨
    -0.07
    ầm
    -0.07
    anj
    -0.06
    upart
    -0.06
    æľ¬æĸĩ为
    -0.06
    èĭ±æĸĩåŃĹ
    -0.06
    ramework
    -0.06
    uros
    -0.06
    POSITIVE LOGITS
    enance
    0.07
    heimer
    0.07
    dee
    0.07
    impa
    0.07
    akup
    0.07
     qed
    0.07
    ä¸įè¿ĩæĿ¥
    0.07
     gai
    0.07
    dain
    0.06
     Ler
    0.06
    Activations Density 0.052%

    No Known Activations