© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16895
    Prev
    Next
    INDEX
    Explanations

    is

    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
    ï¸ı
    -0.07
    æľīæѤ
    -0.07
    èĩªæĭĶ
    -0.07
    =='
    -0.07
    ='_
    -0.07
     capable
    -0.06
    gram
    -0.06
    ci
    -0.06
    zel
    -0.06
     '%'
    -0.06
    POSITIVE LOGITS
    ä»Ģä¹Īåij¢
    0.09
     _______,
    0.08
    orch
    0.07
    /is
    0.07
    ellow
    0.07
    пей
    0.07
    à¹Ģà¸Ķียวà¸ģัà¸ļ
    0.07
     $
    0.07
    ãĢĬ
    0.06
     usu
    0.06
    Activations Density 0.030%

    No Known Activations