© 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. 3242
    Prev
    Next
    INDEX
    Explanations

    numbers followed by comma

    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
    <<<<
    -0.08
    ertools
    -0.08
    ouw
    -0.08
    äºĴ帮
    -0.07
    اعة
    -0.07
    orrent
    -0.07
    åįģéĩĮ
    -0.07
    ×ķר×Ļ×Ŀ
    -0.07
    è´¨çļĦ
    -0.07
    è¿Ļä¹Īåģļ
    -0.07
    POSITIVE LOGITS
    inas
    0.07
     اÙĦÙħÙĪاÙģÙĤ
    0.06
    æīĵåį¡
    0.06
    agar
    0.06
    enger
    0.06
    liny
    0.06
    ,
    0.06
     immortal
    0.06
    ä¹łæĥ¯æĢ§
    0.06
     stesso
    0.05
    Activations Density 0.876%

    No Known Activations