© 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. 12388
    Prev
    Next
    INDEX
    Explanations

    subsequent events or steps

    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
    姿
    -0.07
    Suppress
    -0.07
    uplic
    -0.07
    æķĪçİĩé«ĺ
    -0.07
     зада
    -0.06
     cooperating
    -0.06
    è¿Ľè¡Įä¿®æĶ¹
    -0.06
     reflecting
    -0.06
    è¿Ľè¡Į交æµģ
    -0.06
     zmienia
    -0.06
    POSITIVE LOGITS
     viá»ĩc
    0.10
     incorporation
    0.10
    使çĶ¨åĴĮ
    0.10
    æľĢ大éĻIJ度çļĦ
    0.09
     continued
    0.09
     eventual
    0.09
    alement
    0.09
     removal
    0.09
     kelu
    0.09
     adherence
    0.09
    Activations Density 1.256%

    No Known Activations