© 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. 9434
    Prev
    Next
    INDEX
    Explanations

    JetBrains .intellij workspace

    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
    åı£æ¸´
    -0.07
     encaps
    -0.06
    .gov
    -0.06
    çĸ¯
    -0.06
    _album
    -0.06
    èĢ¸
    -0.06
    大水
    -0.06
    åı£å¾Ħ
    -0.06
    容éĩı
    -0.06
    expired
    -0.06
    POSITIVE LOGITS
     workspace
    0.11
    Workspace
    0.11
     Workspace
    0.11
    workspace
    0.10
    .workspace
    0.09
    /workspace
    0.09
    emacs
    0.09
     vscode
    0.09
    _workspace
    0.08
     workflow
    0.08
    Activations Density 0.424%

    No Known Activations