© 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. 212
    Prev
    Next
    INDEX
    Explanations

    vectors

    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
    bett
    -0.21
    uebas
    -0.20
    DeltaTime
    -0.20
     Buen
    -0.20
    Uvs
    -0.20
     FlatButton
    -0.20
     Craw
    -0.19
    (nonatomic
    -0.19
    UNET
    -0.19
    -pill
    -0.19
    POSITIVE LOGITS
     vectors
    0.43
     vector
    0.40
    vector
    0.35
     vec
    0.31
     Vector
    0.31
    -vector
    0.29
    vec
    0.29
    _vectors
    0.27
    ectors
    0.26
     Vec
    0.26
    Activations Density 0.718%

    No Known Activations