© 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. 49923
    Prev
    Next
    INDEX
    Explanations

    combined or composite

    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
    ampe
    -0.08
    gie
    -0.08
    ä¸Ģéģį
    -0.07
    驻马
    -0.07
    aso
    -0.07
    udo
    -0.07
    лÑĮе
    -0.07
    klang
    -0.07
    ripper
    -0.07
    第ä¸Ģæī¹
    -0.07
    POSITIVE LOGITS
     combined
    0.20
    combined
    0.19
    å¤įåIJĪ
    0.18
    _combined
    0.18
    Combined
    0.18
     Combined
    0.17
     composite
    0.16
    å¤įåIJĪåŀĭ
    0.16
    èģĶåIJĪ
    0.15
    èģĶåIJĪä½ĵ
    0.14
    Activations Density 0.283%

    No Known Activations