© 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. 21163
    Prev
    Next
    INDEX
    Explanations

    strong emotions and desires

    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
    oused
    -0.06
    丢
    -0.05
    yll
    -0.05
    spi
    -0.05
    marsh
    -0.05
    è¨Ģä¹ĭ
    -0.05
     admissions
    -0.05
    ÑıÑĢ
    -0.05
     admission
    -0.05
     nud
    -0.05
    POSITIVE LOGITS
     Osman
    0.06
     îmb
    0.06
    æĦŁæ¿Ģ
    0.06
    ÑĢоб
    0.05
    olid
    0.05
     blocks
    0.05
    emun
    0.05
    æķ´ä¸ª
    0.05
    rons
    0.05
     debido
    0.05
    Activations Density 0.001%

    No Known Activations