© 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. 54961
    Prev
    Next
    INDEX
    Explanations

    referring to similar relationships

    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
    Negative Logits
    çīĪæĿĥå½Ĵ
    -0.08
    .dat
    -0.07
     hozz
    -0.07
    icke
    -0.07
    creativecommons
    -0.07
    ourcing
    -0.07
     Rok
    -0.07
    大é¹ı
    -0.07
    lado
    -0.07
    Injected
    -0.07
    POSITIVE LOGITS
    对åħ¶ä»ĸ
    0.11
    综åIJĪæĢ§
    0.09
    èģļçĦ¦
    0.09
    对åIJĦç§į
    0.08
    æĺ¯åħ³äºİ
    0.08
     focusing
    0.08
    æĬ½è±¡
    0.08
     focused
    0.08
    åħ¨éĿ¢
    0.08
     focuses
    0.08
    Activations Density 0.290%

    No Known Activations