© 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. 863
    Prev
    Next
    INDEX
    Explanations

    refers to information

    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
    ierz
    -0.08
    _interfaces
    -0.08
    第äºĮ大
    -0.07
     Nog
    -0.07
    èļģ
    -0.07
    该款
    -0.07
    cze
    -0.07
    ä»Ĺ
    -0.07
    oyer
    -0.07
    èİĺ
    -0.07
    POSITIVE LOGITS
    æĮĩçļĦæĺ¯
    0.10
    æĺ¯æĮĩåľ¨
    0.10
    æĺ¯æĮĩ
    0.09
    æĮĩ
    0.09
    å°±æĺ¯æĮĩ
    0.08
     whereby
    0.08
    æĮĩçļĦ
    0.08
    sig
    0.07
     refers
    0.07
    顾åIJįæĢĿä¹ī
    0.07
    Activations Density 0.401%

    No Known Activations