© 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. 11116
    Prev
    Next
    INDEX
    Explanations

    software licenses and code comments

    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
    -
    -0.10
    /
    -0.08
    èµ·åĪ°
    -0.07
    heng
    -0.07
    -based
    -0.07
     '
    -0.06
     etc
    -0.06
     Gang
    -0.06
    ville
    -0.06
    -se
    -0.06
    POSITIVE LOGITS
    åĮ»èį¯åį«çĶŁ
    0.08
    缺ä¸Ģ
    0.08
    èıģ
    0.08
    æĻĵ举
    0.07
    ENER
    0.07
     геогÑĢаÑĦи
    0.07
    ÏĢει
    0.07
    cape
    0.07
    gespr
    0.07
    resher
    0.07
    Activations Density 0.001%

    No Known Activations