© 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. 10420
    Prev
    Next
    INDEX
    Explanations

    organometallic compounds

    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
    åħ¨ä½ĵåijĺå·¥
    -0.07
    ariat
    -0.06
    pq
    -0.06
    burgh
    -0.06
    å¼łå°ı
    -0.06
     prest
    -0.06
    ndrome
    -0.06
    brook
    -0.06
    ä»İä¸Ģ个
    -0.06
    åķĨä¸ļ模å¼ı
    -0.06
    POSITIVE LOGITS
    ×Ļ׳×ķ
    0.08
    转移
    0.08
    ivery
    0.08
    OSH
    0.08
     transfer
    0.08
    engo
    0.08
    HING
    0.08
    _transfer
    0.08
     Transfer
    0.08
    kau
    0.08
    Activations Density 0.041%

    No Known Activations