© 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. 18729
    Prev
    Next
    INDEX
    Explanations

    try, can, please

    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
     nih
    -0.06
    eln
    -0.06
    ÑĤил
    -0.06
    è¾°
    -0.06
    zens
    -0.06
    Ãły
    -0.06
    etc
    -0.06
    人ä¹ĭ
    -0.05
    aday
    -0.05
    pty
    -0.05
    POSITIVE LOGITS
     Eck
    0.06
    æł·çļĦ
    0.06
    çĥĺ
    0.05
    解
    0.05
    说罢
    0.05
    ÑĸÑģÑĤÑĮ
    0.05
    عÙĦ
    0.05
    º
    0.05
    å°ıæľī
    0.05
    ongs
    0.05
    Activations Density 0.011%

    No Known Activations