© 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. 1890
    Prev
    Next
    INDEX
    Explanations

    submarine service

    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
    еÑĩе
    -0.07
    odo
    -0.07
    رج
    -0.07
    abat
    -0.07
    erland
    -0.07
    ÛĮÙħاÙĨ
    -0.07
    çĦ¶åIJİæĺ¯
    -0.07
    å°±æĺ¯è¿Ļæł·
    -0.07
    asco
    -0.07
    awa
    -0.06
    POSITIVE LOGITS
    vÄĽ
    0.07
     Scalars
    0.06
     canh
    0.06
    pil
    0.06
    comm
    0.06
    .Clone
    0.06
    åŁĶ
    0.06
    rels
    0.06
    ä»İåĵªéĩĮ
    0.06
    çļĦ大éŨ
    0.06
    Activations Density 0.462%

    No Known Activations