© 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. 50549
    Prev
    Next
    INDEX
    Explanations

    defining or declaring

    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
    awah
    -0.07
    azar
    -0.06
    表çİ°åľ¨
    -0.06
    pliance
    -0.06
    richter
    -0.06
    uman
    -0.06
    .webkit
    -0.06
    emen
    -0.06
    ston
    -0.06
    mage
    -0.06
    POSITIVE LOGITS
     definition
    0.12
    å®ļä¹ī
    0.11
     definitions
    0.11
    definition
    0.10
    å®ļä¹īçļĦ
    0.10
     defini
    0.10
    å®ļä¹īäºĨ
    0.10
    çļĦå®ļä¹ī
    0.10
    defines
    0.10
     Definition
    0.10
    Activations Density 0.030%

    No Known Activations