© 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. 21300
    Prev
    Next
    INDEX
    Explanations

    sudden events or their aftermath

    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
    ä¸İä»ĸ人
    -0.06
    æĬij
    -0.05
    ÃŃch
    -0.05
    *)_
    -0.05
    efined
    -0.05
    -word
    -0.05
    @email
    -0.05
    ¦
    -0.05
     word
    -0.05
     falls
    -0.05
    POSITIVE LOGITS
     briefly
    0.06
    valo
    0.06
    Brief
    0.06
     abrupt
    0.06
    ihen
    0.06
    Mess
    0.06
     temporarily
    0.05
    ä¸Ńå¿ĥ
    0.05
    误ä¼ļ
    0.05
    ufe
    0.05
    Activations Density 0.006%

    No Known Activations