© 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. 19911
    Prev
    Next
    INDEX
    Explanations

    INTRODUCTION and season

    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
    家åĸ»
    -0.07
    epak
    -0.07
    irus
    -0.07
    integrazione
    -0.07
    isateur
    -0.06
    veda
    -0.06
    漬ãģij
    -0.06
     RESPONSABIL
    -0.06
    ervi
    -0.06
     ÙħرÙĪر
    -0.06
    POSITIVE LOGITS
    0.06
    尽管
    0.05
    .
    0.05
     to
    0.05
    Âł
    0.05
    åĪ¶åĽ¾
    0.05
    elo
    0.05
     entertained
    0.05
    c
    0.04
    -
    0.04
    Activations Density 0.003%

    No Known Activations