© 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. 10289
    Prev
    Next
    INDEX
    Explanations

    to be clauses

    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
    ração
    -0.08
    encontre
    -0.08
    åħ¬åı¸æĭ¥æľī
    -0.08
    ÙģÙĦ
    -0.07
    áo
    -0.07
    icismo
    -0.07
    ä¸ĵé¢ĺåŃ¦ä¹ł
    -0.07
    ýt
    -0.07
    amai
    -0.07
    çĥŃéŨæݨèįIJ
    -0.07
    POSITIVE LOGITS
    ï¸ı
    0.08
    以ä¸Ĭå°±æĺ¯åħ³äºİ
    0.07
    s
    0.07
     has
    0.07
     is
    0.07
    ìķ¼
    0.06
     have
    0.06
    omet
    0.06
    为çĶ±
    0.06
    çļĦ
    0.06
    Activations Density 0.078%

    No Known Activations