© 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. 9005
    Prev
    Next
    INDEX
    Explanations

    satellite, GmbH, Co, Umaria, Alfonso

    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
    à¹Īà¸Ńà¸ĩ
    -0.07
    -away
    -0.07
    osan
    -0.07
    uttle
    -0.07
    ×ķ×Ļ
    -0.07
    imli
    -0.07
    anding
    -0.07
     halnya
    -0.07
    eland
    -0.07
    çĪĨäºĨ
    -0.07
    POSITIVE LOGITS
    æĦı
    0.08
    éĻħ
    0.07
    ails
    0.07
    驼
    0.07
    ளà¯į
    0.07
     Lod
    0.07
     behalf
    0.07
    áŁĭ
    0.07
    stick
    0.07
    witz
    0.06
    Activations Density 0.001%

    No Known Activations