© 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. 18233
    Prev
    Next
    INDEX
    Explanations

    concrete and construction materials

    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
     flea
    -0.07
    .gs
    -0.07
    -fold
    -0.07
    èĪªæµ·
    -0.07
    .seek
    -0.07
    åį°æŁĵ
    -0.07
    è¿ĩå±±
    -0.07
    åĪĪ
    -0.07
    çĮİ
    -0.07
    éķĬ
    -0.07
    POSITIVE LOGITS
    æ··åĩĿåľŁ
    0.14
     beton
    0.13
    æ°´æ³¥
    0.13
    æµĩçŃij
    0.12
    çłĤæµĨ
    0.11
    éĴ¢çŃĭ
    0.11
     Concrete
    0.11
     concrete
    0.11
     béton
    0.11
     беÑĤон
    0.11
    Activations Density 0.073%

    No Known Activations