© 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. 65158
    Prev
    Next
    INDEX
    Explanations

    spill or leakage

    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
    ÙĩÙĨ
    -0.07
    ovac
    -0.07
    erat
    -0.07
     imposed
    -0.06
    åīĶéĻ¤
    -0.06
    czyn
    -0.06
    éĶ¢
    -0.06
     chiếu
    -0.06
    ä¸Ģè½®
    -0.06
     pre
    -0.06
    POSITIVE LOGITS
     leakage
    0.13
     spill
    0.12
    æ³Ħæ¼ı
    0.12
    溢
    0.12
     spills
    0.12
     leaking
    0.12
    æ³Ħéľ²
    0.12
    溢åĩº
    0.12
    æ¼ı
    0.11
     spilled
    0.11
    Activations Density 0.113%

    No Known Activations