© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19607
    Prev
    Next
    INDEX
    Explanations

    ask

    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
    еÑĢб
    -0.05
    ä½Ĩä¹Łæľī
    -0.05
     differently
    -0.05
    peek
    -0.05
    lü
    -0.05
    家çĶ¨
    -0.05
    lj
    -0.05
    ool
    -0.05
    yntax
    -0.05
    Ùĩ
    -0.05
    POSITIVE LOGITS
    anggar
    0.06
    дей
    0.06
     preferably
    0.06
    lops
    0.06
    atele
    0.06
     dowol
    0.06
    cede
    0.06
    dos
    0.05
    é¥Ńèıľ
    0.05
    oha
    0.05
    Activations Density 0.001%

    No Known Activations