© 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. 42060
    Prev
    Next
    INDEX
    Explanations

    question or problem

    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
    orm
    -0.08
    äten
    -0.07
    äte
    -0.07
    à¸Ńะà¹Ħรà¸ļà¹īาà¸ĩ
    -0.07
     cuer
    -0.07
    å²ģçļĦæŶåĢĻ
    -0.07
    çī¹å¾ģæĺ¯
    -0.07
     Bloss
    -0.07
    umos
    -0.07
    allah
    -0.07
    POSITIVE LOGITS
     posed
    0.09
    -worthy
    0.07
    jam
    0.06
    blem
    0.06
    itta
    0.06
    ä¸įçŁ¥æīĢ
    0.06
    olith
    0.06
     ÐŁÑĥÑĤ
    0.06
    posed
    0.06
    æīĢè°ĵ
    0.06
    Activations Density 0.041%

    No Known Activations