© 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. 21001
    Prev
    Next
    INDEX
    Explanations

    flooding damage and 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
    é¡·
    -0.07
    iau
    -0.07
    imen
    -0.07
    cht
    -0.07
    antine
    -0.07
    çĶŁç´ł
    -0.06
    大大å°ı
    -0.06
    nst
    -0.06
     Pera
    -0.06
    yip
    -0.06
    POSITIVE LOGITS
    è¯ĪéªĹ罪
    0.06
    Õ¡Õ¾
    0.05
    èļģ
    0.05
     низ
    0.05
     ÑĢеле
    0.05
     ниж
    0.05
     inund
    0.05
    ัà¸Ķ
    0.05
    iv
    0.04
    æĮ¡
    0.04
    Activations Density 0.009%

    No Known Activations