© 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. 47928
    Prev
    Next
    INDEX
    Explanations

    x, y, z coordinates and axes

    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
    trap
    -0.08
    arach
    -0.08
    æķ´å¥Ĺ
    -0.08
    çĢļ
    -0.07
    graf
    -0.07
    pollo
    -0.07
    archs
    -0.07
    caffold
    -0.07
     staples
    -0.07
    åIJĦ级
    -0.07
    POSITIVE LOGITS
    -space
    0.06
     speakers
    0.06
    ob
    0.06
    æĮģ
    0.06
    æĹłåħ³
    0.06
    çļĦ空éĹ´
    0.06
     Speakers
    0.06
     space
    0.06
    amespace
    0.06
    érer
    0.06
    Activations Density 0.006%

    No Known Activations