© 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. 40650
    Prev
    Next
    INDEX
    Explanations

    code definitions

    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
    KR
    -0.07
    大ä¸Ģ
    -0.06
    æł·çļĦ
    -0.06
     Besar
    -0.06
    æĻĸ
    -0.06
     Guerrero
    -0.06
    ä¾Ī
    -0.06
    _submit
    -0.06
    anas
    -0.06
     Altre
    -0.06
    POSITIVE LOGITS
    ãģĿãĤĤãģĿãĤĤ
    0.08
    åİŁæĿ¥æĺ¯
    0.08
    æľīçļĦæĺ¯
    0.07
    港
    0.07
    ling
    0.07
    pto
    0.07
    olon
    0.07
    port
    0.07
     Port
    0.07
    micro
    0.07
    Activations Density 0.061%

    No Known Activations