© 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. 21829
    Prev
    Next
    INDEX
    Explanations

    unforgettable travel experiences

    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
     normally
    -0.06
    å·§åIJĪ
    -0.06
    è¿ĩ头
    -0.05
    宣
    -0.05
    èħ®
    -0.05
    ately
    -0.05
    urgeon
    -0.05
    åģľ
    -0.05
    -num
    -0.05
    lässlich
    -0.05
    POSITIVE LOGITS
    night
    0.06
     sekadar
    0.06
    å¾Ĺèµ·
    0.06
    å©¿
    0.06
    åĵģ缸
    0.06
    åĿļå®ŀ
    0.06
    ive
    0.06
    æīĢ以çİ°åľ¨
    0.06
    lege
    0.06
    ÛĮÙģ
    0.06
    Activations Density 0.010%

    No Known Activations