© 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. 27226
    Prev
    Next
    INDEX
    Explanations

    semiconductor dielectric or

    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
    opf
    -0.09
    bote
    -0.08
    FTER
    -0.08
     Rasul
    -0.08
    åıĭæĥħéĵ¾æİ¥
    -0.08
    .raise
    -0.07
    onas
    -0.07
    缸åħ³æݨèįIJ
    -0.07
    olino
    -0.07
    ipel
    -0.07
    POSITIVE LOGITS
    ént
    0.07
    å°Ķ夫
    0.07
    vem
    0.06
    egis
    0.06
    ä½į
    0.06
     soi
    0.06
    åħĭå°Ķ
    0.06
    å°Ķåħĭ
    0.06
    ä½įçļĦ
    0.06
     hum
    0.06
    Activations Density 1.196%

    No Known Activations