© 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. 15605
    Prev
    Next
    INDEX
    Explanations

    remove property

    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
     [,
    -0.07
    egger
    -0.07
    ocks
    -0.07
    éĩįéĺ³
    -0.07
     ($)
    -0.07
    Mage
    -0.07
    caffold
    -0.07
    以åīįçļĦ
    -0.07
    grim
    -0.06
    ç½ijé¦ĸ页
    -0.06
    POSITIVE LOGITS
    hi
    0.07
     Verst
    0.07
    ä¸ĩäºĭ
    0.07
    ä¸ŃéĺŁ
    0.06
    engesch
    0.06
    ješ
    0.06
    u
    0.06
    abi
    0.06
    ä¸ŃçĶŁ
    0.06
    etos
    0.06
    Activations Density 0.023%

    No Known Activations