© 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. 37805
    Prev
    Next
    INDEX
    Explanations

    Finland and Finnish things

    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
    leston
    -0.09
    ittle
    -0.07
    алÑĮÑı
    -0.07
    elman
    -0.07
     جÙĪاÙĨ
    -0.07
    asic
    -0.07
    ấp
    -0.06
     Tch
    -0.06
     Somma
    -0.06
    ellar
    -0.06
    POSITIVE LOGITS
    èĬ¬åħ°
    0.16
     Finnish
    0.16
     Finland
    0.15
     finland
    0.15
     Helsinki
    0.12
     Nordic
    0.11
     Eston
    0.11
    .fi
    0.11
    ãĥķãĤ£ãĥ³
    0.11
     Suom
    0.10
    Activations Density 0.202%

    No Known Activations