© 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. 150
    Prev
    Next
    INDEX
    Explanations

    change string

    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
     Clintons
    -0.41
     ×Ķ×ķ×ĵ
    -0.31
     RoundedRectangle
    -0.30
    /Observable
    -0.28
     pestic
    -0.28
     enthus
    -0.27
    主è¦ģéĽĨä¸Ń
    -0.27
     filmy
    -0.27
    OrNil
    -0.26
     MILF
    -0.26
    POSITIVE LOGITS
    äºĨ好å¤ļ
    0.30
    è¿Ļ个èģĮä¸ļ
    0.30
    éĹºèľľ
    0.25
    çļĦéĤ£ä¸Ģ
    0.25
     string
    0.24
    ç¥Ľæĸij
    0.24
     zach
    0.24
    åĭł
    0.22
    æĪ¢
    0.22
     airstrikes
    0.22
    Activations Density 8.219%

    No Known Activations