© 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. 21331
    Prev
    Next
    INDEX
    Explanations

    "same" followed by nouns

    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
     Stutt
    -0.07
    лее
    -0.07
    _OBJ
    -0.07
    纲è¦ģ
    -0.07
    AGO
    -0.07
    è¾ĥ为
    -0.07
    ember
    -0.07
    ä»Ļåı°
    -0.07
    åĩ½
    -0.07
    chia
    -0.07
    POSITIVE LOGITS
     same
    0.14
    åIJĮæł·çļĦ
    0.13
    缸åIJĮçļĦ
    0.13
    same
    0.13
    缸åIJĮ
    0.12
     Same
    0.10
    åIJĮãģĺ
    0.10
     mesmos
    0.10
    Same
    0.10
     mêmes
    0.10
    Activations Density 0.082%

    No Known Activations