© 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. 21125
    Prev
    Next
    INDEX
    Explanations

    transcend, crosses, test of time

    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
     ÑĪи
    -0.06
    agon
    -0.06
    çĿ¿
    -0.05
    åĢ¾
    -0.05
    å¤ķ
    -0.05
    ÑģоÑĤ
    -0.05
    ¹
    -0.05
    ÑĨеп
    -0.05
    üs
    -0.05
    ault
    -0.05
    POSITIVE LOGITS
    ç»´
    0.06
    ishes
    0.06
    ming
    0.06
    æĪIJ为ä¸Ģç§į
    0.06
    çķĮçļĦ
    0.06
     Dimension
    0.06
     dimension
    0.06
    Poor
    0.06
    pls
    0.06
    åı¦å¤ĸä¸Ģ个
    0.06
    Activations Density 0.004%

    No Known Activations