© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18794
    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
    ÙħÙħ
    -0.06
    orphic
    -0.06
    olec
    -0.06
    èģļ
    -0.06
    并讲è¯Ŀ
    -0.06
     vac
    -0.06
    宿
    -0.05
    æĽ²
    -0.05
    æĥ
    -0.05
    изи
    -0.05
    POSITIVE LOGITS
     delve
    0.06
    ery
    0.06
    ernal
    0.06
    el
    0.06
    ilig
    0.06
    สà¸ĩ
    0.05
    idão
    0.05
    ampo
    0.05
    å«£
    0.05
     depths
    0.05
    Activations Density 0.000%

    No Known Activations