© 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. 38172
    Prev
    Next
    INDEX
    Explanations

    classification, release, or creation of things

    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
    åľ¨çº¿éĺħ读
    -0.07
    idden
    -0.07
    elius
    -0.07
     váºŃy
    -0.06
    ãĤĴè¨Ńç½®
    -0.06
     ÙĪأش
    -0.06
    uvia
    -0.06
    Ø´ÙĪ
    -0.06
    æĺ¯ä½ł
    -0.06
    å½ĵä»ĸ们
    -0.06
    POSITIVE LOGITS
    à¹ģละà¸ģาร
    0.12
    anje
    0.12
    /rem
    0.11
    /rec
    0.10
    /up
    0.10
     کردÙĨ
    0.10
    ление
    0.10
    /reset
    0.10
    ание
    0.10
    ваннÑı
    0.10
    Activations Density 0.433%

    No Known Activations