© 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. 50120
    Prev
    Next
    INDEX
    Explanations

    conjunctions and clause starters

    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
    etus
    -0.07
    ä¸įå¿ĺ
    -0.07
    oke
    -0.07
    maat
    -0.07
    å°ĸçļĦ
    -0.07
    æ´»äºĨ
    -0.06
    管çIJĨè§ĦèĮĥ
    -0.06
    ä¸įä»ħæĺ¯
    -0.06
    åIJİåĽł
    -0.06
    ÐŁÐ¡
    -0.06
    POSITIVE LOGITS
    åıªå¥½
    0.14
    åıªèĥ½
    0.13
    å°±åıªèĥ½
    0.13
    åıªèĥ½åľ¨
    0.13
    åıªèĥ½éĢļè¿ĩ
    0.13
    åıªèĥ½çĶ¨
    0.11
     nonetheless
    0.11
    æĪijåıªå¥½
    0.10
     nevertheless
    0.10
    åıªå¾Ĺ
    0.10
    Activations Density 0.335%

    No Known Activations