© 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. 7374
    Prev
    Next
    INDEX
    Explanations

    meta viewport content

    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
    uks
    -0.07
    áĢ¯áĢ¶
    -0.07
    ÙĪÙĨÙĩ
    -0.06
    çľ¼çľĭ
    -0.06
    api
    -0.06
    [][
    -0.06
    æºIJåİ¿
    -0.06
    صد
    -0.06
    leben
    -0.06
     nostalg
    -0.06
    POSITIVE LOGITS
    asel
    0.08
    çıĪ
    0.07
    arel
    0.07
    Executing
    0.07
    Illuminate
    0.07
    shal
    0.07
    縮
    0.07
    itif
    0.07
    TERM
    0.07
    浩çī¹
    0.07
    Activations Density 0.016%

    No Known Activations