© 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. 38576
    Prev
    Next
    INDEX
    Explanations

    separators in code

    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
    ushima
    -0.06
    porter
    -0.06
     Wonder
    -0.06
    身
    -0.06
    schluss
    -0.06
    ramer
    -0.06
    oon
    -0.06
    Seb
    -0.06
     re
    -0.06
    Ùģا
    -0.06
    POSITIVE LOGITS
    AVED
    0.08
    Ä©nh
    0.07
    otin
    0.07
    jó
    0.07
    ãĤ¤ãĤº
    0.07
    Ãłi
    0.07
    éros
    0.07
    ÙħاÙĩ
    0.07
    ismer
    0.07
    sic
    0.07
    Activations Density 0.517%

    No Known Activations