© 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. 20036
    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
    -0.06
    Âł
    -0.05
    åĭº
    -0.05
    |
    -0.05
    /
    -0.05
    好
    -0.05
    1
    -0.05
    Å
    -0.05
    ãĢģ
    -0.05
    ext
    -0.05
    POSITIVE LOGITS
    кана
    0.07
    ÑĩиÑĤ
    0.07
    --[
    0.07
    alizada
    0.07
    alizado
    0.07
    ãģ£ãģ±
    0.07
    czeÅĽ
    0.07
    minos
    0.07
    Symbols
    0.06
     Büy
    0.06
    Activations Density 0.000%

    No Known Activations