© 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. 10731
    Prev
    Next
    INDEX
    Explanations

    MRI, GHz, T, dynamic

    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
    æ¶īåıĬçļĦ
    -0.08
    ä¸ĢæŦ
    -0.07
    åIJijä½ł
    -0.07
    åĨįçĶŁèĥ½æºIJ
    -0.07
    æĭĨè£ħ
    -0.06
     Soros
    -0.06
    ushi
    -0.06
     пеÑĢео
    -0.06
    ÙĦÙĬÙĩ
    -0.06
    Broken
    -0.06
    POSITIVE LOGITS
     sensitive
    0.08
    æķıæĦŁçļĦ
    0.08
    åĩºèº«çļĦ
    0.07
    -sensitive
    0.07
    åĽłä¸ºè¿ĻäºĽ
    0.07
     discrimin
    0.07
    ensitive
    0.07
     nhạy
    0.07
     Discrim
    0.07
    ager
    0.07
    Activations Density 0.167%

    No Known Activations