© 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. 42591
    Prev
    Next
    INDEX
    Explanations

    dental, cell, metal, letters, MT

    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
    ur
    -0.07
    annie
    -0.06
    ัà¹īà¸Ļ
    -0.06
    ège
    -0.06
    .Usage
    -0.06
    ân
    -0.06
    åį·
    -0.06
    ä»°
    -0.06
    anto
    -0.06
    ingen
    -0.06
    POSITIVE LOGITS
    æĪĸåħ¶
    0.10
     })).
    0.08
    åij¨ä¸Ģèĩ³
    0.08
    稱çĤº
    0.07
    称ä¹ĭ为
    0.07
    ecker
    0.07
    ICOS
    0.07
    ä¸ĢæŶ
    0.07
    称为
    0.07
    ç§°ä½ľ
    0.07
    Activations Density 0.332%

    No Known Activations