© 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. 28507
    Prev
    Next
    INDEX
    Explanations

    margin, margins, safety margin

    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
    ä¸įæį¢
    -0.09
    ä¹ĭå®Ŀ
    -0.09
    ourd
    -0.09
    ultat
    -0.08
    åįĥæĸ¹
    -0.08
    örd
    -0.08
    edio
    -0.08
    éĵģé¾Ļ
    -0.07
    odie
    -0.07
    iedy
    -0.07
    POSITIVE LOGITS
     margin
    0.11
     margins
    0.10
    Margin
    0.10
    å®īåħ¨
    0.10
    è£ķ
    0.10
     Margin
    0.09
    ä½Ļè£ķ
    0.09
    _MARGIN
    0.09
    çķĻåĩº
    0.09
     safety
    0.09
    Activations Density 0.080%

    No Known Activations