© 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. 56331
    Prev
    Next
    INDEX
    Explanations

    buildings and architecture

    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
    åħħæ²Ľ
    -0.08
    °
    -0.08
    oty
    -0.07
    заÑĢ
    -0.07
    شت
    -0.07
    å¾ĢæĺĶ
    -0.07
    è£ħåľ¨
    -0.07
    æĶ¯æµģ
    -0.07
     Territory
    -0.07
    è·¯ä¸Ĭ
    -0.06
    POSITIVE LOGITS
     buildings
    0.11
     building
    0.10
    åĢĴå¡Į
    0.10
    建çŃijçļĦ
    0.10
    é³ŀ
    0.10
    建çŃij
    0.10
    /build
    0.10
    aub
    0.09
     зданиÑı
    0.09
     edific
    0.09
    Activations Density 0.121%

    No Known Activations