© 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. 17727
    Prev
    Next
    INDEX
    Explanations

    Is or express mathematical operations

    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
    วย
    -0.08
    .toObject
    -0.07
    Ùģر
    -0.07
    ÑijÑĢ
    -0.07
    è¾Ĺ
    -0.07
    AT
    -0.07
     doÄŁr
    -0.07
    âĢ¦**
    -0.07
    rando
    -0.07
     flow
    -0.07
    POSITIVE LOGITS
     chac
    0.07
    tis
    0.06
    _INCLUDED
    0.06
    ercul
    0.06
     Haust
    0.06
    podob
    0.06
     BCH
    0.06
    -popup
    0.06
    ARED
    0.06
     اÙĦعص
    0.06
    Activations Density 0.001%

    No Known Activations