© 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. 22785
    Prev
    Next
    INDEX
    Explanations

    modification notification

    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
    ænd
    -0.07
    æľ¬ç«ĻæīĢæľī
    -0.07
    å±Ĩ
    -0.07
     Harness
    -0.07
    件çļĦ
    -0.07
    optimized
    -0.07
    ì¤Ģ
    -0.06
    mano
    -0.06
     Fountain
    -0.06
    uid
    -0.06
    POSITIVE LOGITS
    omar
    0.07
    æĢ§å¼º
    0.07
    nger
    0.07
    ãĤ¹ãĥĪãĥ©
    0.07
    iÄį
    0.07
    ikit
    0.06
    lv
    0.06
     Brand
    0.06
    μαÏĦο
    0.06
    Merchant
    0.06
    Activations Density 0.431%

    No Known Activations