© 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. 17141
    Prev
    Next
    INDEX
    Explanations

    command-line utilities like awk, sed, jq

    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
    åĮħ
    -0.06
    馨
    -0.06
     respir
    -0.05
    ائب
    -0.05
    çī¢
    -0.05
    adék
    -0.05
    wrapped
    -0.05
     phép
    -0.05
    æģ¯
    -0.05
    train
    -0.05
    POSITIVE LOGITS
    erso
    0.06
    åİ»äºĨ
    0.06
    对å¾ħ
    0.06
    決ãĤģ
    0.06
    IME
    0.06
    varez
    0.06
    jung
    0.06
    ç½²
    0.06
    ately
    0.05
    à¹Ģà¸Ĺศ
    0.05
    Activations Density 0.003%

    No Known Activations