© 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. 8496
    Prev
    Next
    INDEX
    Explanations

    plugin configuration

    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
    åļ£
    -0.07
    ÙĪÙĨس
    -0.06
    atti
    -0.06
    halter
    -0.06
    תר
    -0.06
    éļı
    -0.06
    hod
    -0.06
    pite
    -0.06
    arb
    -0.06
    Ŀ
    -0.06
    POSITIVE LOGITS
    ÑĤии
    0.08
    osed
    0.08
    Reusable
    0.08
     opro
    0.08
     oms
    0.07
    ritable
    0.07
    .Provider
    0.07
    obet
    0.07
    åĪ¶å®ľ
    0.07
    woch
    0.07
    Activations Density 0.001%

    No Known Activations