© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 55210
    Prev
    Next
    INDEX
    Explanations

    "the" followed by specific nouns

    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
    缸åħ³èµĦ讯
    -0.08
    uring
    -0.08
    æ°¸
    -0.07
    asuk
    -0.07
    NSS
    -0.07
    ׼×ķ׾
    -0.07
    ober
    -0.06
     Prec
    -0.06
    affe
    -0.06
    .palette
    -0.06
    POSITIVE LOGITS
    æĹłç§ģçļĦ
    0.07
    ä¹ĭæīĢ以
    0.06
    以ä¸ĭåĩłçĤ¹
    0.06
    óta
    0.06
    忽çķ¥äºĨ
    0.06
    æ´ĭæ´ĭ
    0.06
    ä½Ļåħī
    0.06
     anya
    0.06
    åı¯æĥľçļĦæĺ¯
    0.06
    riminator
    0.06
    Activations Density 0.015%

    No Known Activations