© 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. 59893
    Prev
    Next
    INDEX
    Explanations

    legal and financial documents

    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
    kontakt
    -0.07
    angeb
    -0.07
    æľŁ
    -0.07
    artig
    -0.07
    thers
    -0.07
    æijĩæijĩ
    -0.07
    বà§ĩ
    -0.07
    åĪ«
    -0.07
    alnya
    -0.07
    åıĭæĥħéĵ¾æİ¥
    -0.06
    POSITIVE LOGITS
    山大
    0.07
     Neste
    0.07
    æĮīåħ¶
    0.07
    ault
    0.06
    å±±éķĩ
    0.06
    ãģ²ãĤį
    0.06
    ç»ĦæĪIJåijĺ
    0.06
    yman
    0.06
    hatian
    0.06
    ÏĥÏĦε
    0.06
    Activations Density 0.162%

    No Known Activations