© 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. 33077
    Prev
    Next
    INDEX
    Explanations

    ships and maritime vessels

    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
    å´Ĺ
    -0.09
    羿
    -0.08
    tpl
    -0.08
    acular
    -0.08
    åģĩä½ĵ
    -0.08
    impat
    -0.08
    tempts
    -0.08
    Bloc
    -0.08
    [keys
    -0.08
    ^K
    -0.08
    POSITIVE LOGITS
     vessel
    0.08
    çĶ²æĿ¿
    0.08
     onboard
    0.08
     hull
    0.08
     Ñįкипа
    0.08
    èĪªè¡Į
    0.08
     vessels
    0.08
     crew
    0.08
    æīĢè½½
    0.08
     aboard
    0.08
    Activations Density 0.119%

    No Known Activations