© 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. 51171
    Prev
    Next
    INDEX
    Explanations

    treaty, inquiry, declaration, settlement

    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
    å¤ĸçľģ
    -0.10
    visor
    -0.09
     poda
    -0.08
    CHK
    -0.07
    çľģå¤ĸ
    -0.07
    _REASON
    -0.07
    åľ¨åħ¨çľģ
    -0.07
    ntax
    -0.07
    ecto
    -0.07
     oppon
    -0.07
    POSITIVE LOGITS
     treaty
    0.11
    åĽ½éĻħ社ä¼ļ
    0.10
     diplomatic
    0.10
     treaties
    0.10
     worldwide
    0.10
    å¤ļè¾¹
    0.10
    æĪIJåijĺåĽ½
    0.09
    çŃīåĽ½éĻħ
    0.09
    åIJĦåĽ½
    0.09
    åıijå±ķä¸ŃåĽ½å®¶
    0.09
    Activations Density 0.021%

    No Known Activations