© 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. 21311
    Prev
    Next
    INDEX
    Explanations

    countries and street names

    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
    atom
    -0.05
    oto
    -0.05
    дке
    -0.05
    æĿĤçī©
    -0.05
     Bloody
    -0.05
     reta
    -0.05
    alu
    -0.05
    åħ³äºĨ
    -0.05
    äº
    -0.05
    etro
    -0.05
    POSITIVE LOGITS
    寡
    0.06
    ourage
    0.06
    è¿ĩçĶŁæĹ¥
    0.05
    oscope
    0.05
     Cub
    0.05
    hold
    0.05
    ãĤģ
    0.05
    urse
    0.05
    наÑĢ
    0.05
    çĵ
    0.05
    Activations Density 0.017%

    No Known Activations