© 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. 21420
    Prev
    Next
    INDEX
    Explanations

    code and file structure

    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
    urry
    -0.06
    ä¸į顺
    -0.06
    akas
    -0.06
     entirety
    -0.05
    oa
    -0.05
    ÑĢÑı
    -0.05
    à¸Ĺัà¹īà¸ĩสิà¹īà¸Ļ
    -0.05
    漫
    -0.05
    è¦ģåĽł
    -0.05
    ä»»ä½ķä¸Ģæĸ¹
    -0.05
    POSITIVE LOGITS
    cet
    0.06
    igit
    0.06
    æĸĩåĮĸæ°ĽåĽ´
    0.06
    erd
    0.05
    gång
    0.05
    å°±æĺ¯è¿Ļä¹Ī
    0.05
    åѦåłĤ
    0.05
    жига
    0.05
    chema
    0.05
    bull
    0.05
    Activations Density 0.026%

    No Known Activations