© 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. 40052
    Prev
    Next
    INDEX
    Explanations

    complexes, interactions, or coupling

    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
    åĽłä¸ºåħ¶
    -0.07
    æł¹æį®åħ¶
    -0.07
    åIJĵ人
    -0.06
    人为
    -0.06
    为ä»ĸ人
    -0.06
    çĶ±äºİåħ¶
    -0.06
    å¦Ĥåħ¶
    -0.06
    ighton
    -0.06
    ç²¹
    -0.06
    大åĬĽå¼ĺæī¬
    -0.06
    POSITIVE LOGITS
     بÙĬÙĨÙĩÙħا
    0.15
     relationship
    0.14
    åıĮæĸ¹çļĦ
    0.14
    åħ³ç³»
    0.14
    åħ¬åı¸ä¸İ
    0.13
     interaction
    0.13
    relationship
    0.13
     Relationship
    0.12
    åħ³ç³»çļĦ
    0.12
     between
    0.12
    Activations Density 0.374%

    No Known Activations