© 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. 21607
    Prev
    Next
    INDEX
    Explanations

    you want or you have

    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
    èī²
    -0.06
    etra
    -0.06
    èī²çļĦ
    -0.05
    ablement
    -0.05
    urette
    -0.05
    æĻ®éģį
    -0.05
     Deta
    -0.05
    ereien
    -0.05
     triangular
    -0.05
    åŁİ乡建设
    -0.05
    POSITIVE LOGITS
    Ñĸз
    0.05
    class
    0.05
    евÑģкого
    0.05
    anis
    0.05
     ï¼ŀ
    0.05
    ¹
    0.05
    heen
    0.05
    ãģıãģĦ
    0.05
    itzer
    0.05
    lemen
    0.05
    Activations Density 0.011%

    No Known Activations