© 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. 8280
    Prev
    Next
    INDEX
    Explanations

    code block terminators

    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
    è®°
    -0.07
    lsa
    -0.07
    计
    -0.07
    æĹı
    -0.06
    ore
    -0.06
    éĻĽ
    -0.06
    -store
    -0.06
     cul
    -0.06
    Store
    -0.06
    ç±ģ
    -0.06
    POSITIVE LOGITS
    appings
    0.09
    æķĻèĤ²åѦçĶŁ
    0.07
    è¿Ľè¡ĮçłĶ究
    0.07
     Einz
    0.07
     Tanjung
    0.07
     researched
    0.07
     CAUSED
    0.07
    enet
    0.07
    ÐĶФ
    0.07
    èѦæĥķ
    0.07
    Activations Density 0.033%

    No Known Activations