© 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. 16597
    Prev
    Next
    INDEX
    Explanations

    north, south, east, west

    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
    -0.07
    óg
    -0.06
    æł·
    -0.06
    Ĵ
    -0.06
     Gros
    -0.06
    ó
    -0.06
     qualifications
    -0.05
    iner
    -0.05
    å½Ĵ
    -0.05
    ç«łç¨ĭ
    -0.05
    POSITIVE LOGITS
    endere
    0.09
    ieber
    0.09
    ä¸Ģéĥİ
    0.08
    ensem
    0.08
    ASAN
    0.08
    à¤ķरà¥į
    0.08
    itespace
    0.08
    issan
    0.08
    ×ĵ×Ķ
    0.08
    upy
    0.08
    Activations Density 0.004%

    No Known Activations