© 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. 39863
    Prev
    Next
    INDEX
    Explanations

    balanced minimum cuts

    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
    urve
    -0.09
    çħĮ
    -0.08
    igel
    -0.08
    vors
    -0.08
    çĴĩ
    -0.08
    ilight
    -0.07
    第ä¸īä½į
    -0.07
    _advance
    -0.07
    鸾
    -0.07
    æĭīå¼ĢäºĨ
    -0.07
    POSITIVE LOGITS
     contributions
    0.09
    è´¡çĮ®
    0.09
     subtree
    0.09
     Contribution
    0.09
     contribution
    0.08
    æ±ĩ
    0.08
    æ±ĩéĽĨ
    0.08
    èģļ
    0.08
    æ±ĩæĢ»
    0.08
     Contributions
    0.07
    Activations Density 0.010%

    No Known Activations