© 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. 544
    Prev
    Next
    INDEX
    Explanations

    unusual text

    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
    hế
    -0.56
    -League
    -0.32
    letics
    -0.30
    celain
    -0.29
    ellery
    -0.29
    ÙĪضÙĪع
    -0.29
    rarian
    -0.29
    stice
    -0.28
    dling
    -0.28
    byn
    -0.28
    POSITIVE LOGITS
    æĦıè§ģåıįé¦Ī
    0.35
    缸åħ³æĸ°éĹ»
    0.33
    åı¯ä»¥æĽ´å¥½
    0.33
    vanished
    0.32
    ç½ijåıĭè¯Ħ论
    0.32
    ä»İæł¹æľ¬
    0.31
    çĶ¨å¾®ä¿¡
    0.31
    并ä¸įæĦıåij³
    0.30
    çķĻè¨ĢæĿ¿
    0.29
    Türkiye
    0.29
    Activations Density 7.317%

    No Known Activations