© 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. 26680
    Prev
    Next
    INDEX
    Explanations

    tracking, marking, labeling

    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
    emean
    -0.08
    é©»
    -0.07
    èĮ§
    -0.07
    ulai
    -0.07
    hti
    -0.07
    éĺħè§Ī
    -0.07
    æijĬ
    -0.07
    enge
    -0.07
     skl
    -0.07
    覽
    -0.06
    POSITIVE LOGITS
    追踪
    0.13
     tracking
    0.11
     tagging
    0.11
    æłĩè®°
    0.11
     Tracking
    0.11
    è·Łè¸ª
    0.11
     marker
    0.11
     ì¶Ķìłģ
    0.10
    Tracking
    0.10
    tracking
    0.10
    Activations Density 0.243%

    No Known Activations