© 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. 50777
    Prev
    Next
    INDEX
    Explanations

    origin or column designation

    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
    ikas
    -0.07
    æģ¢å¤įåĪ°
    -0.07
    æĮĩæłĩ
    -0.07
    ä¼łäºº
    -0.07
    æī¦
    -0.07
    окÑģи
    -0.07
     Gon
    -0.06
    ander
    -0.06
    esson
    -0.06
    iative
    -0.06
    POSITIVE LOGITS
    便å°Ĩ
    0.10
    对ä¸ĢäºĽ
    0.10
    对éĤ£äºĽ
    0.10
    çļĦçī©åĵģ
    0.09
    å°ĨæīĢæľī
    0.09
    对æīĢ
    0.09
    对è¿ĻäºĽ
    0.09
    æĬĬæīĢæľī
    0.08
    å°±å°Ĩ
    0.08
    åı¯å°Ĩ
    0.08
    Activations Density 0.616%

    No Known Activations