© 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. 17657
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and formulas

    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
    屡
    -0.05
     prima
    -0.05
    cene
    -0.04
     general
    -0.04
    èĥľ
    -0.04
     Lynn
    -0.04
    循çݯ
    -0.04
    å°¾æ°Ķ
    -0.04
    emon
    -0.04
     kin
    -0.04
    POSITIVE LOGITS
    žite
    0.07
    logger
    0.07
    olumn
    0.06
    Ùĩر
    0.06
    continued
    0.06
     **âĢ¢
    0.06
    gek
    0.06
    èİĵ
    0.06
    pson
    0.06
     köln
    0.06
    Activations Density 0.001%

    No Known Activations