© 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. 27476
    Prev
    Next
    INDEX
    Explanations

    pound currency symbol and prices

    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
    hood
    -0.09
    warzys
    -0.08
    ÑĮÑı
    -0.08
    cule
    -0.08
    lor
    -0.08
    cules
    -0.08
    à¸Ħà¹Ĥà¸Ļ
    -0.07
    å¦Ĥæŀľä½łå¯¹
    -0.07
    anco
    -0.07
    以ä¸Ĭå°±æĺ¯åħ³äºİ
    -0.07
    POSITIVE LOGITS
    ãģĬ
    0.08
    ï¸ı
    0.08
    ï¸İ
    0.08
    ãģĬå¾Ĺ
    0.08
    ãģµãģĨãģ«
    0.07
    rawdÄĻ
    0.07
    ลฯ
    0.07
    åĨħç»ı
    0.07
    ¤
    0.07
    人æĹł
    0.07
    Activations Density 0.017%

    No Known Activations