© 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. 21886
    Prev
    Next
    INDEX
    Explanations

    Numbers and letters

    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
    orge
    -0.06
     Strut
    -0.06
    annot
    -0.06
    ieve
    -0.06
    éĽªæ¢¨
    -0.06
    anko
    -0.05
    eneric
    -0.05
    oth
    -0.05
    ingk
    -0.05
    æĪŁ
    -0.05
    POSITIVE LOGITS
    åĨįæİ¥
    0.05
    à¹Īà¸Ļ
    0.05
    olla
    0.05
     padrão
    0.05
    缸æ¯Ķ
    0.05
    oller
    0.05
    eger
    0.05
    aban
    0.05
    omba
    0.05
    æİ¥
    0.05
    Activations Density 0.012%

    No Known Activations