© 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. 46920
    Prev
    Next
    INDEX
    Explanations

    first column or phase

    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
    ulait
    -0.08
     riêng
    -0.08
    евиÑĩ
    -0.08
    rchive
    -0.08
    uptools
    -0.08
    ntag
    -0.08
    ìľ¼ë¡ľëıĦ
    -0.08
     mãi
    -0.08
    人æĦı
    -0.08
    spath
    -0.08
    POSITIVE LOGITS
    Âł
    0.08
    ï
    0.06
     ï
    0.06
    幸
    0.06
     âĢ¦
    0.06
    æ±Ĺ
    0.06
     ris
    0.06
    0.05
    ³³
    0.05
    æľ¬é¢ĺ
    0.05
    Activations Density 0.003%

    No Known Activations