© 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. 12507
    Prev
    Next
    INDEX
    Explanations

    as much as possible

    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
    ä¸ĢäºĽéĹ®é¢ĺ
    -0.08
    ught
    -0.08
    å¤ļç§įå½¢å¼ı
    -0.07
    Ú¾ÛĮ
    -0.07
    æĽ´å¤ļ精彩
    -0.07
    缸å½ĵ
    -0.07
    çļĦä»»ä½ķ
    -0.07
    ä»»ä½ķéĹ®é¢ĺ
    -0.07
    æķĪåĬĽçļĦ
    -0.07
    .parameters
    -0.07
    POSITIVE LOGITS
    encontre
    0.08
    ains
    0.08
    ä½ĨåıĪ
    0.07
    amment
    0.07
    acement
    0.07
    éĽį
    0.07
    ots
    0.07
     mẽ
    0.07
    avera
    0.06
    zej
    0.06
    Activations Density 0.012%

    No Known Activations