© 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. 32976
    Prev
    Next
    INDEX
    Explanations

    self-consistent, symmetry, message passing

    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
    Õ®
    -0.08
    igraph
    -0.08
    ×ľ×ª
    -0.07
    _usec
    -0.07
    omic
    -0.07
    Õ¥Õ¿
    -0.07
    Fmt
    -0.07
    atty
    -0.07
    سÙĦاÙħ
    -0.07
    лÑĮÑĤи
    -0.07
    POSITIVE LOGITS
    çĭ¬
    0.07
    çij¶
    0.07
    orld
    0.07
     optimistic
    0.07
    å¹³åĿĩ
    0.07
     reality
    0.07
    _loop
    0.07
     average
    0.07
     modelling
    0.07
    çĭ¬ç§Ģ
    0.07
    Activations Density 0.013%

    No Known Activations