© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64223
    Prev
    Next
    INDEX
    Explanations

    Byzantine, Export, Canada, Security

    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
    ocab
    -0.08
    åĽº
    -0.08
    åľŃ
    -0.07
    æ°¸
    -0.07
    شاء
    -0.06
    à§ģà¦ķ
    -0.06
    \n
    -0.06
     foregoing
    -0.06
    gu
    -0.06
    å±ħ
    -0.06
    POSITIVE LOGITS
    usia
    0.10
    اÙĦÙĬا
    0.08
    åħ¶ä¸Ģ
    0.07
    vania
    0.07
    ÙĪÙĨÙĬا
    0.07
    ä¹ĭä¸ĢçļĦ
    0.07
    emiz
    0.07
    ushman
    0.07
    alia
    0.07
    ubre
    0.07
    Activations Density 0.048%

    No Known Activations