© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1662
    Prev
    Next
    INDEX
    Explanations

    water

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    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
    ushima
    -0.23
    çģ«çĦ°
    -0.22
     dust
    -0.22
     Flame
    -0.22
     Dust
    -0.21
    çĩĥçĥ§
    -0.20
    åİļ
    -0.19
    çĩ®
    -0.19
    çĩİ
    -0.19
     furnace
    -0.19
    POSITIVE LOGITS
     water
    0.42
    æ°´
    0.38
    water
    0.35
    æ¸ħæ¾Ī
    0.35
    æ°´è´¨
    0.33
    æ°´ä¸Ń
    0.32
    æ°´éĩı
    0.31
     Water
    0.31
    .water
    0.30
    _water
    0.28
    Activations Density 3.609%

    No Known Activations