© 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. 21694
    Prev
    Next
    INDEX
    Explanations

    as ... as

    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
    çī¹èī²å°ıéķĩ
    -0.05
    editary
    -0.05
    价款
    -0.05
    çľĭçĤ¹
    -0.05
    人家
    -0.05
    .people
    -0.05
     terms
    -0.05
    声èī²
    -0.05
     unto
    -0.05
    alahan
    -0.05
    POSITIVE LOGITS
    ttp
    0.06
    æĶ¿æ²»ä¸Ĭ
    0.06
    çī¢
    0.06
    sts
    0.06
    -collapse
    0.06
    è¿ľäºĨ
    0.06
    kori
    0.05
    ocks
    0.05
    una
    0.05
    ÙħÙĨ
    0.05
    Activations Density 0.015%

    No Known Activations