© 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. 1634
    Prev
    Next
    INDEX
    Explanations

    alphanumeric identifiers

    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
    ĸī
    -0.23
    é¾Ł
    -0.22
    éĢļ讯
    -0.21
    .addCell
    -0.20
    frica
    -0.20
    èĥĮéĿ¢
    -0.19
     backs
    -0.19
     beach
    -0.18
    ANDLE
    -0.18
    rios
    -0.18
    POSITIVE LOGITS
    onestly
    0.28
     masturbating
    0.23
    passport
    0.22
     UITableViewController
    0.21
    ialized
    0.20
    ACHI
    0.20
     Dag
    0.20
    omez
    0.20
    etroit
    0.20
    .BorderSize
    0.20
    Activations Density 1.001%

    No Known Activations