© 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. 2321
    Prev
    Next
    INDEX
    Explanations

    hosting services

    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
    FlowLayout
    -0.21
     lowes
    -0.21
    -License
    -0.20
     todd
    -0.19
    æµģéĢļ
    -0.19
     NEWS
    -0.19
    øj
    -0.19
    tees
    -0.19
    thy
    -0.18
    âĸĴ
    -0.18
    POSITIVE LOGITS
    .AddTransient
    0.26
     cloud
    0.25
    .cloud
    0.23
    äºij
    0.23
    æIJ¦
    0.22
    \/\/
    0.22
    åħ¬ç½ij
    0.21
    -cloud
    0.21
    UInteger
    0.20
    âĺģ
    0.20
    Activations Density 0.776%

    No Known Activations