© 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. 37913
    Prev
    Next
    INDEX
    Explanations

    being forced or tasked

    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
    를
    -0.10
    °
    -0.09
    áĥ§
    -0.08
    ï¸ı
    -0.08
    çIJĨå·¥åѦéĻ¢
    -0.08
    ÅĤów
    -0.08
    <dyn
    -0.08
    å¾ħ人
    -0.08
    té
    -0.07
    nya
    -0.07
    POSITIVE LOGITS
    äºĨä¸Ģ次
    0.10
    äºĨä¸Ģå®ļ
    0.10
    äºĨä¸Ģ
    0.10
    ãģ¹ãģį
    0.08
    bidden
    0.08
    ibold
    0.08
    erro
    0.08
    er
    0.08
    æīĢè°ĵçļĦ
    0.08
    ately
    0.08
    Activations Density 0.003%

    No Known Activations