© 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. 22358
    Prev
    Next
    INDEX
    Explanations

    default values or placeholders

    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
    ignet
    -0.08
    NodeId
    -0.08
    ici
    -0.07
    antry
    -0.07
    åĩĮ天
    -0.07
    جة
    -0.07
    rgan
    -0.07
    DataContext
    -0.07
    subplot
    -0.07
    leben
    -0.07
    POSITIVE LOGITS
     laure
    0.07
    pons
    0.07
    all
    0.06
    åľ¨éĿŀ
    0.06
    illa
    0.06
    _static
    0.06
    orz
    0.06
    Sn
    0.06
     Spo
    0.06
    Ef
    0.06
    Activations Density 0.009%

    No Known Activations