© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22290
    Prev
    Next
    INDEX
    Explanations

    Visual Studio or studio album

    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
    تÙĦ
    -0.05
    ↵
    -0.05
    Ķ
    -0.05
    ↵↵
    -0.05
    ä½įçļĦ
    -0.05
    lec
    -0.05
    marked
    -0.05
     common
    -0.05
    ники
    -0.05
    æĽ²
    -0.05
    POSITIVE LOGITS
    pheric
    0.08
    aylor
    0.07
    èĥľåĪ©åı¬å¼Ģ
    0.07
    keit
    0.07
    éłĥãģ«
    0.07
    offerta
    0.07
    ewel
    0.07
    ÑģÑı
    0.07
    aket
    0.07
    为äºĨ解åĨ³
    0.07
    Activations Density 0.015%

    No Known Activations