© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20669
    Prev
    Next
    INDEX
    Explanations

    versus

    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
    æª
    -0.06
     whilst
    -0.06
    пок
    -0.05
    ä¸ĢçĤ¹åĦ¿
    -0.05
    æħķåIJį
    -0.05
    rieg
    -0.05
     osta
    -0.05
    end
    -0.05
    eny
    -0.05
    ulence
    -0.05
    POSITIVE LOGITS
    iban
    0.06
     formally
    0.06
    peon
    0.06
    è¡·
    0.05
    exper
    0.05
    lij
    0.05
    -lite
    0.05
    åĽ´çĿĢ
    0.05
    EventManager
    0.05
    à¸ļุà¸į
    0.05
    Activations Density 0.080%

    No Known Activations