© 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. 15179
    Prev
    Next
    INDEX
    Explanations

    spatial and numerical relationships

    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
     oppure
    -0.06
    æĪĸæĺ¯
    -0.06
    ilie
    -0.06
     DÃŃ
    -0.06
    und
    -0.06
    borg
    -0.06
     corresponding
    -0.05
    æĪĸèĢħ
    -0.05
    bah
    -0.05
    orn
    -0.05
    POSITIVE LOGITS
    ä¼ģä¸ļåħ³ç³»
    0.08
    ÑĮем
    0.08
    ÑĢÑĥб
    0.08
    phans
    0.07
     izman
    0.07
    ocking
    0.07
    रà¥įफ
    0.07
    ç³»ç»ŁçŃī
    0.07
    glieder
    0.07
    ÑĢиз
    0.07
    Activations Density 0.183%

    No Known Activations