© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17166
    Prev
    Next
    INDEX
    Explanations

    matematyka in Polish or Turkish contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tulev
    -0.06
     chai
    -0.06
    ulin
    -0.06
    razil
    -0.06
     ÑģебÑı
    -0.05
    Geral
    -0.05
    vall
    -0.05
    åĽ½å®ī
    -0.05
     empreend
    -0.05
    纲è¦ģ
    -0.05
    POSITIVE LOGITS
    urious
    0.05
    otomy
    0.05
     rec
    0.05
    led
    0.05
    æľīæķĪæıIJåįĩ
    0.05
    åIJĦ
    0.05
    ç¼ĺæķħ
    0.05
    upu
    0.05
    icho
    0.05
    ieg
    0.05
    Activations Density 0.473%

    No Known Activations