© 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. 20396
    Prev
    Next
    INDEX
    Explanations

    expressing frustration

    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
    æĪĸå°ij
    -0.06
    и
    -0.06
    баланÑģи
    -0.05
    ensed
    -0.05
    lob
    -0.05
    outh
    -0.05
    Ñģад
    -0.05
    ãģŁãģ³
    -0.05
    ammu
    -0.05
    amik
    -0.05
    POSITIVE LOGITS
    zi
    0.06
    女éĥİ
    0.06
     ÙĦØ·
    0.06
    aisin
    0.06
    ycz
    0.06
    apat
    0.06
     dern
    0.06
    æ²¹æĿ¡
    0.06
     disillusion
    0.06
    zü
    0.06
    Activations Density 0.003%

    No Known Activations