© 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. 34479
    Prev
    Next
    INDEX
    Explanations

    agreement to keep quiet

    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
    æľ¬åľºæ¯ĶèµĽ
    -0.07
    ients
    -0.07
     antren
    -0.07
    æľīå¿Ĺ
    -0.07
    unittest
    -0.06
    幸åŃĺèĢħ
    -0.06
    алан
    -0.06
    声æĺİèĢħ
    -0.06
    aksa
    -0.06
    è¿Ļæł·çļĦä¸Ģ个
    -0.06
    POSITIVE LOGITS
    æĢł
    0.08
     allegedly
    0.08
    their
    0.07
    vez
    0.07
     their
    0.07
    åħ¶å¯¹
    0.07
    eding
    0.07
    itzt
    0.07
    ä»ĸ们对
    0.06
    è¾±
    0.06
    Activations Density 0.867%

    No Known Activations