© 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. 39032
    Prev
    Next
    INDEX
    Explanations

    irrigation district

    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
    cul
    -0.08
    culus
    -0.07
    «
    -0.07
    ipher
    -0.07
    ä¼´çĿĢ
    -0.06
    elay
    -0.06
    hein
    -0.06
     fys
    -0.06
    cu
    -0.06
    kul
    -0.06
    POSITIVE LOGITS
    etr
    0.08
    eggi
    0.07
    odb
    0.07
    istos
    0.07
    apie
    0.07
    ORTE
    0.07
    éĻ¢åĨħ
    0.07
    Pod
    0.07
    áĥĶáĥĹ
    0.07
    ê¸ī
    0.07
    Activations Density 0.586%

    No Known Activations