© 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. 21332
    Prev
    Next
    INDEX
    Explanations

    greeting or introduction phrases

    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
    agin
    -0.07
     Vinc
    -0.06
    ihan
    -0.06
    æ±ķ
    -0.06
    ruz
    -0.06
    èĢģ天
    -0.06
    个ä¸ĵä¸ļ
    -0.06
     matéri
    -0.05
    prov
    -0.05
     меж
    -0.05
    POSITIVE LOGITS
    æīĢçŁ¥
    0.06
    одно
    0.05
    æī¾åĪ°èĩªå·±
    0.05
    æĿ¥çľĭ
    0.05
    修饰
    0.05
     اÙĦÙĪ
    0.05
    Fo
    0.05
    Ùĥ
    0.05
    Ñĸб
    0.05
     fo
    0.05
    Activations Density 0.010%

    No Known Activations