© 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. 49169
    Prev
    Next
    INDEX
    Explanations

    code blocks and commands

    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
    à¥įà¤Ł
    -0.08
    åŀĭ人æīį
    -0.08
    éļıçĿĢå¹´é¾ĦçļĦå¢ŀéķ¿
    -0.07
    anax
    -0.07
    ddl
    -0.07
    ption
    -0.07
    交çĶµ
    -0.07
    à§ģষ
    -0.07
    å¿ı
    -0.07
    ä¸įå®ĮçļĦ
    -0.07
    POSITIVE LOGITS
     temporarily
    0.08
    à¸Ĭัà¹Īวà¸Ħราว
    0.07
    å²±
    0.07
    à¸Ńิà¸ĩ
    0.07
    åĪĩæį¢
    0.07
     ÙħؤÙĤت
    0.07
    ungk
    0.07
    åĪ¶
    0.07
     regained
    0.07
    è¿Ľè¡Įæĵįä½ľ
    0.07
    Activations Density 0.124%

    No Known Activations