© 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. 46526
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions and punctuation

    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
    epis
    -0.07
     أعد
    -0.07
    åħ¶ä»ĸ类似éĹ®é¢ĺ
    -0.07
    enek
    -0.06
    æĭ§
    -0.06
    orama
    -0.06
    illance
    -0.06
    ahari
    -0.06
    cro
    -0.06
     Uploaded
    -0.06
    POSITIVE LOGITS
    èĢĮçİ°åľ¨
    0.12
     whereas
    0.10
    ä½Ĩçİ°åľ¨
    0.10
    æĪijåį´
    0.09
    èĢĮæĪij们
    0.09
    èĢĮæĪij
    0.09
    çİ°åľ¨æĪij
    0.09
    èĢĮå¦Ĥä»Ĭ
    0.09
    èĢĮä»Ĭ
    0.08
    çİ°åľ¨çľĭæĿ¥
    0.08
    Activations Density 0.179%

    No Known Activations