© 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. 20919
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with numbers and symbols

    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
    ät
    -0.06
    ets
    -0.06
     bip
    -0.05
    itu
    -0.05
    impl
    -0.05
    ek
    -0.05
    ET
    -0.05
    джеÑĤ
    -0.05
     carn
    -0.05
    ortal
    -0.04
    POSITIVE LOGITS
    odik
    0.07
    ulta
    0.07
    ressing
    0.06
    aveled
    0.06
     Aires
    0.06
    abaj
    0.06
    renz
    0.05
    æķĻäºİ
    0.05
    reis
    0.05
    lassian
    0.05
    Activations Density 0.002%

    No Known Activations