© 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. 178
    Prev
    Next
    INDEX
    Explanations

    model

    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
     practition
    -0.28
     lowes
    -0.26
     gangbang
    -0.26
    #ga
    -0.25
     pornstar
    -0.25
    notated
    -0.24
    rawid
    -0.24
     ikea
    -0.23
    pedia
    -0.23
    éparation
    -0.23
    POSITIVE LOGITS
     model
    0.48
    模åŀĭ
    0.44
    model
    0.39
     models
    0.36
    -model
    0.35
     based
    0.34
    _model
    0.33
     Model
    0.32
    Model
    0.31
     calculations
    0.31
    Activations Density 1.584%

    No Known Activations