© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 31668
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations

    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
    顺
    -0.07
    çļĦæĪij们
    -0.07
    oot
    -0.06
    è¿Ļä¹Ī大
    -0.06
    imore
    -0.06
    ØŃاÙħ
    -0.06
    æīĭå¿ĥ
    -0.06
    è£ķ
    -0.06
    åĩºå¥ĩ
    -0.06
    âĢ¦
    -0.06
    POSITIVE LOGITS
    å¥Ķ
    0.08
     ():
    0.08
    uai
    0.08
    uar
    0.07
    amba
    0.07
    æ±Ľ
    0.07
    ç§ijåѦçłĶ究éĻ¢
    0.07
    berger
    0.07
    å°Ķ夫
    0.07
    piler
    0.07
    Activations Density 0.039%

    No Known Activations