© 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. 16444
    Prev
    Next
    INDEX
    Explanations

    Trump Orders

    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
    -none
    -0.07
    å´İ
    -0.07
    ourd
    -0.07
    oproject
    -0.07
    anity
    -0.06
    rina
    -0.06
    abee
    -0.06
    æĭĽçĶŁä¸ĵä¸ļ
    -0.06
    ypi
    -0.06
    Uvs
    -0.06
    POSITIVE LOGITS
    ahu
    0.08
    idal
    0.08
    åİĭå²ģ
    0.07
    jac
    0.07
    åĿij
    0.07
    avern
    0.07
    =utf
    0.07
    että
    0.06
    å°ģ
    0.06
    idos
    0.06
    Activations Density 0.001%

    No Known Activations