© 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. 39861
    Prev
    Next
    INDEX
    Explanations

    wood veneer or masonry veneer

    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
    -0.08
    emn
    -0.06
    æ³¢
    -0.06
    åIJ¸çĿĽ
    -0.06
    con
    -0.06
    Broker
    -0.06
    æĭĽ
    -0.06
    brook
    -0.06
     Hum
    -0.06
    elib
    -0.05
    POSITIVE LOGITS
    κει
    0.09
    ụt
    0.08
    æĪĸåħ¶
    0.08
    ĻĤ
    0.07
    çĶļèĩ³æĺ¯
    0.07
    igd
    0.07
    ª½
    0.07
    ново
    0.07
    erguson
    0.07
    agos
    0.07
    Activations Density 0.167%

    No Known Activations