© 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. 22190
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ä¸įæĢĿ
    -0.06
     Galer
    -0.06
    emble
    -0.06
    lında
    -0.05
    umpur
    -0.05
    isti
    -0.05
    lag
    -0.05
    ÑģаÑĢ
    -0.05
    arsed
    -0.05
    lagen
    -0.05
    POSITIVE LOGITS
    建æĸ°
    0.06
    é«ĺ级
    0.06
    æ¯Ķè¾ĥé«ĺ
    0.06
    ibilité
    0.05
    親åĪĩ
    0.05
     \"{
    0.05
    建åįİ
    0.05
     overall
    0.05
    иÑĤелÑĮ
    0.05
    æģŃ
    0.05
    Activations Density 0.000%

    No Known Activations