© 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. 2664
    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
    .handleChange
    -0.22
    .handleSubmit
    -0.22
     IonicPage
    -0.20
     Gow
    -0.20
    ASM
    -0.19
    .getElementsBy
    -0.19
     Contributors
    -0.19
    @SuppressWarnings
    -0.19
    ,:);↵
    -0.19
    FLT
    -0.19
    POSITIVE LOGITS
    åĻĻ
    0.28
    ocaly
    0.25
    ='".
    0.24
    .CodeAnalysis
    0.22
    ãĥµ
    0.21
    lijah
    0.21
     adulte
    0.20
    tees
    0.20
    dives
    0.20
    idebar
    0.19
    Activations Density 0.000%

    No Known Activations