© 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. 16250
    Prev
    Next
    INDEX
    Explanations

    description and purpose

    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
    vie
    -0.08
    ä»Ķ
    -0.07
    =yes
    -0.07
    evo
    -0.07
    lder
    -0.07
    rst
    -0.07
     зака
    -0.06
    aring
    -0.06
    HEADER
    -0.06
    );}
    -0.06
    POSITIVE LOGITS
     &
    0.08
    Touches
    0.08
    &action
    0.07
    اÙĦÙī
    0.07
    resher
    0.06
    åıĬ设å¤ĩ
    0.06
    纸ä¸ļ
    0.06
    unday
    0.06
    ä¹ĭæŃĮ
    0.06
    æģķ
    0.06
    Activations Density 0.122%

    No Known Activations