© 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. 45391
    Prev
    Next
    INDEX
    Explanations

    Core tip

    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
    éĶ¦æ¶Ľ
    -0.10
    avent
    -0.08
    为èį£
    -0.07
    uant
    -0.07
    åįĥçĻ¾
    -0.07
     conosco
    -0.07
     %[
    -0.07
    eed
    -0.07
    wic
    -0.07
    çļĦç§įåŃIJ
    -0.06
    POSITIVE LOGITS
    Built
    0.09
    inen
    0.08
     built
    0.07
    eder
    0.07
    lat
    0.07
    ìĶ©
    0.07
     indeed
    0.06
    à¹Ģà¸Ļà¹īà¸Ļ
    0.06
    Iterable
    0.06
     each
    0.06
    Activations Density 0.001%

    No Known Activations