© 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. 34071
    Prev
    Next
    INDEX
    Explanations

    concepts related to systems, matter, and organization

    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
    udos
    -0.07
    ouser
    -0.07
    æĿ¥åĽŀ
    -0.07
    غر
    -0.06
     COMMENTS
    -0.06
    _pull
    -0.06
    ingga
    -0.06
     glitch
    -0.06
    å½ĵæŶçļĦ
    -0.06
    äºĽè®¸
    -0.06
    POSITIVE LOGITS
    åı¯ä»¥åĪĨ为
    0.12
    主è¦ģåĪĨ为
    0.12
    åı¯åĪĨ为
    0.12
    åĪĨç±»
    0.10
    æ¦Ĥè¿°
    0.09
    绪
    0.09
    第ä¸ĢèĬĤ
    0.09
     basics
    0.09
    形形èī²
    0.09
    åĪĨ为
    0.09
    Activations Density 0.451%

    No Known Activations