© 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. 11035
    Prev
    Next
    INDEX
    Explanations

    neoantigen, occult HBV, olestra, piezoelectric, transdifferentiation, Ajax, charter schools, apparent competition, John Henryism

    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
    æĨ¨
    -0.07
    nger
    -0.07
    å¤©çľŁ
    -0.06
    éĢıæĺİ
    -0.06
    åģ¶
    -0.06
    obl
    -0.06
     opaque
    -0.06
     («
    -0.06
    羣
    -0.06
    .sb
    -0.06
    POSITIVE LOGITS
    è¿Ļæł·çļĦ人
    0.08
    raph
    0.08
    ationally
    0.08
     tadi
    0.08
    çļĦè¿Ļç§į
    0.07
    enas
    0.07
    åIJįåī¯åħ¶å®ŀ
    0.07
     appunto
    0.07
    ipe
    0.07
    ãģ³
    0.07
    Activations Density 0.245%

    No Known Activations