© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19485
    Prev
    Next
    INDEX
    Explanations

    AI or computer game interaction

    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
    干湿
    -0.06
     Afinal
    -0.06
    ç±»
    -0.05
    ecz
    -0.05
     اÙĦعاب
    -0.05
    ä¸Ńèĭ±
    -0.05
     cleanse
    -0.05
    ằng
    -0.05
    uisse
    -0.05
    éĢĨè¡Į
    -0.05
    POSITIVE LOGITS
    igde
    0.06
    æĭĻ
    0.06
    Ñĩем
    0.06
    .beh
    0.06
    çŃī级
    0.06
    çłĶ究表æĺİ
    0.05
     Companion
    0.05
     deliber
    0.05
    补缺
    0.05
    reve
    0.05
    Activations Density 0.009%

    No Known Activations