© 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. 18183
    Prev
    Next
    INDEX
    Explanations

    difference, sum, or delta

    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
    éĵ®
    -0.08
    ä»·å»ī
    -0.08
    годно
    -0.08
    å·²ä¹ħ
    -0.08
     Prós
    -0.08
     idé
    -0.08
     Perspek
    -0.08
    zung
    -0.08
    ÑģÑģен
    -0.08
    èĵĿåĽ¾
    -0.07
    POSITIVE LOGITS
     consecutive
    0.07
    arr
    0.07
    è®¤çľŁå¼Ģå±ķ
    0.06
    ä¸Ģ级
    0.06
    ToArray
    0.06
     successive
    0.06
    éĻª
    0.06
    大山
    0.06
    à¸Ħร
    0.06
    secutive
    0.06
    Activations Density 0.002%

    No Known Activations