© 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. 3945
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ANDOM
    -0.23
    (CancellationToken
    -0.21
    .Millisecond
    -0.21
    éĶ¶
    -0.21
    ailable
    -0.20
    èħ§
    -0.20
     libertin
    -0.19
    /twitter
    -0.19
    .GPIO
    -0.19
    аблиÑĨ
    -0.19
    POSITIVE LOGITS
    .SwingConstants
    0.26
    engeance
    0.21
    [strlen
    0.20
    .BackgroundImageLayout
    0.20
    cedures
    0.20
     Ground
    0.19
    setProperty
    0.18
    anke
    0.18
    FML
    0.18
    úsqueda
    0.18
    Activations Density 0.000%

    No Known Activations