© 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. 56390
    Prev
    Next
    INDEX
    Explanations

    companies and organizations

    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
    ×Ļרת
    -0.08
     esetén
    -0.08
    oghi
    -0.07
     similar
    -0.07
    atown
    -0.07
    佳人
    -0.07
    icka
    -0.07
    otá
    -0.07
    æľ«å¹´
    -0.07
    å¸Ĥæĸ°
    -0.07
    POSITIVE LOGITS
     themselves
    0.17
     aforementioned
    0.11
     thems
    0.10
    aviest
    0.10
     Ø£ÙĨÙģسÙĩÙħ
    0.10
     mentioned
    0.10
     kojima
    0.09
    åIJĦèĩªçļĦ
    0.08
     listed
    0.08
     outlined
    0.08
    Activations Density 0.676%

    No Known Activations