© 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. 17754
    Prev
    Next
    INDEX
    Explanations

    network components

    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
     Acht
    -0.07
    onnement
    -0.06
    ollo
    -0.06
    ساعدة
    -0.06
    çĩİ
    -0.06
     ÙģÙĬÙĩا
    -0.06
    atern
    -0.06
    isa
    -0.06
    оÑĤи
    -0.06
    หาร
    -0.06
    POSITIVE LOGITS
    jom
    0.06
    st
    0.05
     Ep
    0.05
     напÑĢа
    0.05
     most
    0.05
     whichever
    0.05
    Ep
    0.05
    ä¸Ńä¸İ
    0.05
     ep
    0.05
     dong
    0.05
    Activations Density 0.161%

    No Known Activations