© 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. 16192
    Prev
    Next
    INDEX
    Explanations

    likewise similarly equally

    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
    ä½ij
    -0.08
    æĮ
    -0.06
    WSC
    -0.06
    iette
    -0.06
    ä¸īæĸ¹
    -0.06
    å¤©åľ°
    -0.06
     SAND
    -0.06
    竺
    -0.06
    lands
    -0.06
    tika
    -0.06
    POSITIVE LOGITS
     similarly
    0.14
     likewise
    0.12
    亦çĦ¶
    0.10
    åIJĮæł·
    0.10
     Likewise
    0.09
     Similarly
    0.09
    åIJĮ樣
    0.09
    Similarly
    0.09
     igualmente
    0.09
    ãģĵãģ¡ãĤīãĤĤ
    0.09
    Activations Density 0.085%

    No Known Activations