© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 958
    Prev
    Next
    INDEX
    Explanations

    code terms

    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
     nackte
    -0.26
    hores
    -0.25
     Antworten
    -0.23
     extrad
    -0.22
    tridges
    -0.22
    acades
    -0.22
    --;↵↵
    -0.21
    .unshift
    -0.21
    selling
    -0.21
     tatsäch
    -0.21
    POSITIVE LOGITS
     FindObjectOfType
    0.23
    je
    0.22
    åĽĽä¸ªæĦıè¯Ĩ
    0.21
    -eslint
    0.21
    ted
    0.21
    /*↵
    0.20
    /umd
    0.20
    .CheckBox
    0.20
    ency
    0.20
    ters
    0.19
    Activations Density 0.725%

    No Known Activations