© 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. 2398
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation following 3

    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
    ölf
    -0.08
    endale
    -0.08
    zej
    -0.08
     demais
    -0.07
    ässer
    -0.07
    .Environment
    -0.07
    inition
    -0.07
    à¹Ĩ
    -0.07
    illac
    -0.07
    breaker
    -0.07
    POSITIVE LOGITS
    ÙĦع
    0.08
    egger
    0.08
    Ĺı
    0.07
    ettle
    0.07
    æŀĿèĬ±
    0.07
    лÑĮкÑĥ
    0.07
    çģ£
    0.07
    гоÑĢа
    0.07
    ÄŁlu
    0.07
    undos
    0.07
    Activations Density 0.151%

    No Known Activations