© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19901
    Prev
    Next
    INDEX
    Explanations

    sarcasm

    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
    q
    -0.06
    éĩĬ
    -0.06
    бÑĢи
    -0.06
    resp
    -0.06
    heb
    -0.06
    á»ıng
    -0.06
    ết
    -0.06
    qt
    -0.06
    缸åħ³ä¸ļåĬ¡
    -0.06
    çļĨåı¯
    -0.05
    POSITIVE LOGITS
    stick
    0.06
    onor
    0.05
    -yard
    0.05
     Report
    0.05
     Bert
    0.05
     lies
    0.05
    ffit
    0.05
     but
    0.05
    mitted
    0.05
    sticks
    0.05
    Activations Density 0.001%

    No Known Activations