© 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. 16300
    Prev
    Next
    INDEX
    Explanations

    magnetic sensing assemblies

    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
    czyn
    -0.07
    åĤį
    -0.07
    顾
    -0.07
    ioc
    -0.07
     Kül
    -0.07
    踵
    -0.06
    æĹłæŃ¢
    -0.06
    ullets
    -0.06
    ongi
    -0.06
    åijĽ
    -0.06
    POSITIVE LOGITS
     Independ
    0.08
    antee
    0.08
    åĮħåIJ«çĿĢ
    0.07
     everything
    0.07
    å¹³åı°ä¸Ĭ
    0.07
     containing
    0.07
    reds
    0.07
    åĪĨä¹ĭ
    0.07
    زاÙħ
    0.07
    enus
    0.07
    Activations Density 0.606%

    No Known Activations