© 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. 23186
    Prev
    Next
    INDEX
    Explanations

    Slovak and Czech language and geography

    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
     Brooklyn
    -0.07
    å¾Īæĺ¾çĦ¶
    -0.07
    vaard
    -0.07
    ombang
    -0.07
    atto
    -0.07
    zyb
    -0.07
    æ·®åįĹ
    -0.06
    onden
    -0.06
     zabr
    -0.06
    éģ¨
    -0.06
    POSITIVE LOGITS
     Slovak
    0.12
     Czech
    0.12
     Slovakia
    0.11
    æį·åħĭ
    0.10
    lovak
    0.09
     Bratis
    0.09
     Sloven
    0.09
     Prague
    0.08
     Slov
    0.08
     Slovenia
    0.08
    Activations Density 0.090%

    No Known Activations