© 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. 48659
    Prev
    Next
    INDEX
    Explanations

    name/record/version/trait/remote/corporation

    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
    ahr
    -0.07
    ["_
    -0.07
    .getConfig
    -0.07
     Selengkapnya
    -0.07
    ][]
    -0.07
    æīįæĻº
    -0.07
    åħ¨åĬĽåģļ好
    -0.07
    å¤ĸéĵ¾
    -0.07
    quinho
    -0.07
     à¸ķà¸²à¸¡à¸Ľà¸£à¸°à¹Ģà¸łà¸Ĺ
    -0.07
    POSITIVE LOGITS
    è¿Ŀåıį
    0.07
    çĸ¾
    0.06
    angan
    0.06
    éĢ¼äºº
    0.06
    就对
    0.06
    umé
    0.06
    æķ¢
    0.05
    utre
    0.05
    TT
    0.05
     hil
    0.05
    Activations Density 0.547%

    No Known Activations