© 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. 104
    Prev
    Next
    INDEX
    Explanations

    first person I

    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
    /↵↵↵↵
    -0.26
     MILF
    -0.25
    utschen
    -0.24
     @"";↵
    -0.24
    "default
    -0.24
    -animate
    -0.23
    -Semit
    -0.23
    (iOS
    -0.23
     Palestin
    -0.23
    grily
    -0.23
    POSITIVE LOGITS
     my
    0.29
    请éĹ®
    0.27
     airstrikes
    0.25
    æĪijçİ°åľ¨
    0.25
     myself
    0.24
     I
    0.24
    æĪijçļĦ
    0.23
    æĺ¯æĪijçļĦ
    0.23
     unsuccessfully
    0.23
    my
    0.23
    Activations Density 13.704%

    No Known Activations