© 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. 46584
    Prev
    Next
    INDEX
    Explanations

    distribution and direction

    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
    èģĺ
    -0.07
     verh
    -0.07
    ç½®ä¹ĭ
    -0.07
    å¾ģ
    -0.06
     undercover
    -0.06
    å¾µ
    -0.06
    rung
    -0.06
     Watch
    -0.06
    åıĮèĬĤ
    -0.06
     rung
    -0.06
    POSITIVE LOGITS
    漫
    0.10
    distribution
    0.09
    åĪĨå¸ĥ
    0.09
    åįĬçIJĥ
    0.09
    æķ£
    0.09
    direction
    0.09
     specular
    0.09
    -direction
    0.09
    æľĿåIJij
    0.08
    æķ£çļĦ
    0.08
    Activations Density 0.013%

    No Known Activations