© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3464
    Prev
    Next
    INDEX
    Explanations

    code or markup

    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
    ØŃتÙĬاج
    -0.20
    č
    -0.19
    ij
    -0.19
    ï¼ļ"+
    -0.19
    \admin
    -0.19
    åĿı
    -0.19
    Longrightarrow
    -0.19
    imshow
    -0.19
    åīįçŀ»æĢ§
    -0.19
    NSUserDefaults
    -0.18
    POSITIVE LOGITS
    -lnd
    0.25
    ystems
    0.24
    âļĹ
    0.23
    ~-~-
    0.22
     fkk
    0.22
    imbus
    0.21
     (!((
    0.21
    ongoose
    0.20
    stract
    0.19
     UFC
    0.19
    Activations Density 0.001%

    No Known Activations