© 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. 17175
    Prev
    Next
    INDEX
    Explanations

    years and decades

    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
    asan
    -0.08
    cak
    -0.07
    ovic
    -0.07
    !!,
    -0.07
    esk
    -0.07
    à¹īา
    -0.07
    anon
    -0.07
    åĢĻ
    -0.07
    oz
    -0.07
    iph
    -0.07
    POSITIVE LOGITS
    èĵĭ
    0.07
     [/
    0.07
    çĿ
    0.07
     [,
    0.07
    åŃ¦ä»¥èĩ´
    0.07
    ãģ®ãģĵãģ¨
    0.07
     alternatively
    0.07
     ÙħØ«
    0.06
    ä¸ĢæĹģçļĦ
    0.06
    åŃ¦ä»¥èĩ´çĶ¨
    0.06
    Activations Density 0.001%

    No Known Activations