© 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. 495
    Prev
    Next
    INDEX
    Explanations

    2

    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
    isex
    -0.29
    ðŁĵIJ
    -0.27
    âļĹ
    -0.26
    uckland
    -0.23
    *****č↵
    -0.23
    lasting
    -0.23
    @brief
    -0.23
    >({
    -0.23
    ÙĪاÙģÙĤ
    -0.23
    EEDED
    -0.23
    POSITIVE LOGITS
    -thirds
    0.37
    nd
    0.31
    orgetown
    0.29
     gode
    0.29
    Ùħخاط
    0.27
    å¾Īå¤ļçݩ家
    0.25
     Filme
    0.24
     thirds
    0.23
     näm
    0.23
    游æĪıéĩĮçļĦ
    0.23
    Activations Density 1.859%

    No Known Activations