© 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. 28826
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
    æŦ
    -0.08
    èn
    -0.07
    fas
    -0.07
    ault
    -0.07
    )$/
    -0.06
    ieras
    -0.06
    éĵ¿
    -0.06
    uille
    -0.06
    éħĿ
    -0.06
    å°¤åħ¶æĺ¯
    -0.06
    POSITIVE LOGITS
    å¿«æį·
    0.07
    appers
    0.07
    koa
    0.07
    AsStream
    0.07
    _alias
    0.07
     Informations
    0.07
    åĪ«åIJį
    0.07
    amba
    0.07
     itib
    0.06
    åľ°çĤ¹
    0.06
    Activations Density 0.783%

    No Known Activations