© 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. 21025
    Prev
    Next
    INDEX
    Explanations

    Relative clauses and specifiers

    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
     horiz
    -0.05
    xDB
    -0.05
     recol
    -0.05
     vice
    -0.05
    mise
    -0.05
    å±Ģ
    -0.05
    ideos
    -0.05
    inea
    -0.05
    åĪ¶åīĤ
    -0.05
    DB
    -0.05
    POSITIVE LOGITS
    ieza
    0.06
    olla
    0.06
    обÑĢа
    0.06
    éta
    0.06
    并åıĸå¾Ĺ
    0.06
    enge
    0.06
    并ä¸Ķåľ¨
    0.06
    ATUR
    0.06
    ÙĪÙħت
    0.05
     acorde
    0.05
    Activations Density 0.013%

    No Known Activations