© 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. 17495
    Prev
    Next
    INDEX
    Explanations

    mouth expressions

    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
    åĩĨ
    -0.05
    esel
    -0.05
     zam
    -0.05
     Pack
    -0.05
    avit
    -0.05
     cap
    -0.05
    åłª
    -0.05
     물ìĿĦ
    -0.05
    管çIJĨå±Ģ
    -0.05
     Ordn
    -0.05
    POSITIVE LOGITS
     associates
    0.07
    é³Ħé±¼
    0.07
    åg
    0.07
    istor
    0.07
    ugno
    0.06
    igator
    0.06
     Led
    0.06
    hada
    0.06
     fór
    0.06
     arco
    0.06
    Activations Density 0.003%

    No Known Activations