© 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. 17767
    Prev
    Next
    INDEX
    Explanations

    names of places and organizations

    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
    วม
    -0.07
    EIC
    -0.07
    KEY
    -0.06
    çĿ£å¯Ł
    -0.06
    osl
    -0.06
    TEAM
    -0.06
     Lumpur
    -0.06
    clid
    -0.06
    俯
    -0.06
    çĤĬ
    -0.06
    POSITIVE LOGITS
    again
    0.10
     novamente
    0.08
     again
    0.08
     nuevamente
    0.07
    åıĪä¸Ģ
    0.07
    Again
    0.07
     irresist
    0.07
    åĨį次
    0.07
    emeld
    0.06
    åĨįä¸Ģ次
    0.06
    Activations Density 0.065%

    No Known Activations