© 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. 24462
    Prev
    Next
    INDEX
    Explanations

    prometic gravity news accounts

    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
    çĦ¶å¤§
    -0.08
     keren
    -0.08
    bergen
    -0.07
    Vir
    -0.07
    ÑĢÑĥÑĤ
    -0.07
    çĵ¦å°Ķ
    -0.07
    à¹Ģห
    -0.07
    çĶŁåij½çļĦ
    -0.07
    åħ±åĴĮåĽ½
    -0.07
    æĺłåħ¥
    -0.07
    POSITIVE LOGITS
     ot
    0.06
    UILTIN
    0.06
    æ»
    0.06
    είÏĦε
    0.06
    BlockSize
    0.06
    èĵī
    0.06
    åħ¸
    0.06
     god
    0.06
    çĶļ
    0.06
     universal
    0.06
    Activations Density 0.363%

    No Known Activations