© 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. 39460
    Prev
    Next
    INDEX
    Explanations

    envelope and its modifiers

    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
    ÏģιÏĥ
    -0.08
    burgh
    -0.08
    anyi
    -0.07
    ÙĪتر
    -0.07
    anford
    -0.07
    Ïģια
    -0.07
    Bur
    -0.07
    éªĭ
    -0.07
    欢声
    -0.07
    ä¸įæĩĪ
    -0.07
    POSITIVE LOGITS
     envelope
    0.12
     envelopes
    0.11
    -envelope
    0.10
     envelop
    0.09
    Envelope
    0.09
    velope
    0.09
    amac
    0.07
    é¢ĵ
    0.07
    èµ·ä¼ı
    0.07
    velop
    0.07
    Activations Density 0.006%

    No Known Activations