© 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. 17057
    Prev
    Next
    INDEX
    Explanations

    stem width

    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
    æĢĿæĥ³ä¸Ĭ
    -0.06
     suce
    -0.06
    بÙĪد
    -0.06
     incar
    -0.06
    ç¾¹
    -0.06
     incr
    -0.06
    à¹Īาย
    -0.06
    צ×Ķ
    -0.06
     singled
    -0.06
    ubb
    -0.06
    POSITIVE LOGITS
    oni
    0.06
    Ou
    0.05
     th
    0.05
    è¡ĵ
    0.05
     under
    0.05
     mid
    0.05
    ä¸ĩ件
    0.05
     **
    0.04
    st
    0.04
    ville
    0.04
    Activations Density 0.006%

    No Known Activations