© 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. 2622
    Prev
    Next
    INDEX
    Explanations

    tourism and tourist related words

    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
    ities
    -0.08
    furter
    -0.08
    soever
    -0.08
     comerci
    -0.07
    tered
    -0.07
    ×ķ×ķ
    -0.07
    lessly
    -0.07
    èĬ¯
    -0.07
    /or
    -0.07
    odings
    -0.07
    POSITIVE LOGITS
    èĥľåľ°
    0.11
    ä¸ļçļĦ
    0.09
    /host
    0.07
     Dest
    0.07
    iage
    0.07
    atore
    0.07
    AGER
    0.07
    ê°Ŀ
    0.07
    hone
    0.07
    illon
    0.07
    Activations Density 0.046%

    No Known Activations