© 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. 3394
    Prev
    Next
    INDEX
    Explanations

    age and duration

    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
    รวà¸ĩ
    -0.09
    ively
    -0.09
    shire
    -0.09
    urb
    -0.08
    надÑĨ
    -0.08
    اة
    -0.08
    ÑĩеÑĤÑĭ
    -0.08
    ฯ
    -0.08
    Leaks
    -0.07
    족
    -0.07
    POSITIVE LOGITS
    0.10
    -old
    0.07
    érit
    0.07
    lendir
    0.07
    etting
    0.07
    hood
    0.07
    emma
    0.07
    acson
    0.07
    uada
    0.07
    bedo
    0.07
    Activations Density 0.066%

    No Known Activations