© 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. 17794
    Prev
    Next
    INDEX
    Explanations

    just a phrase

    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
    ometr
    -0.06
    Exactly
    -0.06
    erre
    -0.06
     exactly
    -0.06
    ogos
    -0.06
    unden
    -0.06
     fut
    -0.06
    metro
    -0.05
    оÑĩно
    -0.05
    olit
    -0.05
    POSITIVE LOGITS
    åıijæĮ¥èĩªå·±çļĦ
    0.06
     Auss
    0.06
    essin
    0.06
     sini
    0.06
    èĢĮå·²
    0.06
    ÑĢаÑĤа
    0.05
    prib
    0.05
    åIJ¸å¼ķäºĨä¼Ĺå¤ļ
    0.05
    è¿Ļä¸ªåľ°æĸ¹
    0.05
    entra
    0.05
    Activations Density 0.002%

    No Known Activations