© 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. 23613
    Prev
    Next
    INDEX
    Explanations

    decomposition, splitting, partitioning

    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
     stim
    -0.08
    å¤ļåıij
    -0.07
    ivers
    -0.07
    å¤Ń
    -0.07
    جÙħ
    -0.07
     Technolog
    -0.06
    ÑĢовеÑĢ
    -0.06
    minated
    -0.06
    ateurs
    -0.06
    elsif
    -0.06
    POSITIVE LOGITS
     decomposition
    0.16
    åĪĨ离
    0.14
    åĪĨ解
    0.14
     Decom
    0.13
    æĭĨåĪĨ
    0.13
     splitting
    0.13
    .Split
    0.13
     decom
    0.13
     splits
    0.13
    æĭĨ
    0.12
    Activations Density 0.024%

    No Known Activations