© 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. 50352
    Prev
    Next
    INDEX
    Explanations

    recirculate or recycle

    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
    eles
    -0.08
    ius
    -0.07
     circon
    -0.07
    ayos
    -0.07
     receptive
    -0.07
     Freed
    -0.07
    azza
    -0.07
    μον
    -0.07
    à¸Ļาม
    -0.07
    OrFail
    -0.07
    POSITIVE LOGITS
    loop
    0.10
     feedback
    0.10
     loop
    0.10
    åĽŀæµģ
    0.10
    循çݯ
    0.10
    éĢģåĽŀ
    0.10
    åĽŀçļĦ
    0.10
    åĽŀæĿ¥çļĦ
    0.10
    åĽŀ
    0.10
    ä¸Ģéĥ¨åĪĨ
    0.09
    Activations Density 0.031%

    No Known Activations