© 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. 18004
    Prev
    Next
    INDEX
    Explanations

    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
    messe
    -0.06
    lei
    -0.06
    ison
    -0.06
    irut
    -0.06
    ernet
    -0.06
    leb
    -0.06
    wick
    -0.06
    Å¡ov
    -0.06
    kaan
    -0.06
     Crime
    -0.06
    POSITIVE LOGITS
     tre
    0.06
     toler
    0.05
     sil
    0.05
    åıª
    0.05
    uwen
    0.05
     Tre
    0.05
    ars
    0.05
     vi
    0.05
    ap
    0.05
    奸
    0.05
    Activations Density 0.002%

    No Known Activations