© 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. 21137
    Prev
    Next
    INDEX
    Explanations

    two types

    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
    ardy
    -0.06
    ấn
    -0.06
    asy
    -0.06
    ÑĢоки
    -0.06
    çķĻ
    -0.06
    etas
    -0.06
    aber
    -0.06
     Rounds
    -0.06
     ÑĥдаÑģÑĤÑģÑı
    -0.05
    cen
    -0.05
    POSITIVE LOGITS
    olv
    0.05
     narrow
    0.05
     mostly
    0.05
    æĿ¡ä»¶ä¸ĭ
    0.05
    æĿ¡ä»¶ä¸ĭçļĦ
    0.05
    æĸĽ
    0.05
     score
    0.05
    aldo
    0.05
     Los
    0.05
     largely
    0.05
    Activations Density 0.034%

    No Known Activations