© 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. 9680
    Prev
    Next
    INDEX
    Explanations

    for background, applications, data

    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
    ÙĪÙħÙĬØ©
    -0.07
    é½
    -0.06
    жай
    -0.06
     Certa
    -0.06
    ocl
    -0.06
     Decomp
    -0.06
     mantu
    -0.06
     cla
    -0.06
    hone
    -0.06
    _apply
    -0.06
    POSITIVE LOGITS
    /manage
    0.08
    åıĪæĥ³
    0.07
     ìľĦíķ´ìĦľëĬĶ
    0.07
    åĪĻçĶ±
    0.07
    ä¼ļè®®çĶ±
    0.07
    -turn
    0.07
    çļĦé¦ĸéĢī
    0.07
    éľĢè¦ģçĶ¨
    0.07
    æݨèįIJ使çĶ¨
    0.07
    çļĦè¯Ħä»·æĺ¯
    0.07
    Activations Density 0.384%

    No Known Activations