© 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. 17498
    Prev
    Next
    INDEX
    Explanations

    [i

    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
    stration
    -0.06
    дома
    -0.06
    ç²īä¸Ŀ们
    -0.06
    عزÙĬز
    -0.06
    ÛĮÙĨÚ¯
    -0.06
    fulness
    -0.06
    们
    -0.06
    tons
    -0.06
    ovid
    -0.06
    adow
    -0.05
    POSITIVE LOGITS
    ic
    0.06
    ior
    0.06
    iais
    0.06
    forsch
    0.06
    åĪ°ä¸ŃåĽ½
    0.06
    ié
    0.06
    ed
    0.06
    i
    0.06
    iene
    0.06
    enzen
    0.05
    Activations Density 0.006%

    No Known Activations