© 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. 42169
    Prev
    Next
    INDEX
    Explanations

    particle-verb constructions

    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
    inciple
    -0.07
    abouts
    -0.07
     Conway
    -0.07
    å½¼æѤçļĦ
    -0.07
    subscribe
    -0.07
    kke
    -0.07
    outh
    -0.07
    aderas
    -0.07
    tsky
    -0.07
    styr
    -0.07
    POSITIVE LOGITS
    variably
    0.08
    ugu
    0.07
    luv
    0.07
     enclosed
    0.07
    æĸ¹ä½į
    0.07
    عÙħ
    0.07
    ofer
    0.07
     pulmon
    0.06
     lesbians
    0.06
    onga
    0.06
    Activations Density 0.002%

    No Known Activations