© 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. 21598
    Prev
    Next
    INDEX
    Explanations

    definition or specification

    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
    宫åĨħ
    -0.05
    è¿ĩæĹ©
    -0.05
    anel
    -0.05
     trained
    -0.05
     Intr
    -0.05
     gradually
    -0.05
    olor
    -0.05
     Filos
    -0.05
    aya
    -0.05
     incontourn
    -0.05
    POSITIVE LOGITS
    encontre
    0.06
    recht
    0.06
    даÑĤ
    0.06
    åijĺçļĦ
    0.06
    ÙĨع
    0.06
    stantiate
    0.06
    apg
    0.06
     hôtel
    0.05
    mes
    0.05
    gelijke
    0.05
    Activations Density 0.001%

    No Known Activations