© 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. 19654
    Prev
    Next
    INDEX
    Explanations

    state-of-the-art

    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
     trac
    -0.06
    modern
    -0.05
    ÑĢовиÑĩ
    -0.05
    undo
    -0.05
    rient
    -0.05
    ut
    -0.05
    incontro
    -0.05
    çŃĶå¤į
    -0.05
     modern
    -0.05
    ç§
    -0.05
    POSITIVE LOGITS
    tile
    0.06
    æ°ı
    0.06
    zione
    0.06
     Ãľl
    0.05
    heen
    0.05
    ÅĤada
    0.05
    Since
    0.05
    oya
    0.05
     korist
    0.05
    å·®ãģĹ
    0.05
    Activations Density 0.001%

    No Known Activations