© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1397
    Prev
    Next
    INDEX
    Explanations

    boolean values

    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
    esteem
    -0.24
    :numel
    -0.20
    éĶIJ
    -0.19
    éķij
    -0.19
     par
    -0.19
     safeg
    -0.18
     glBind
    -0.18
    èµ°åĬ¿åĽ¾
    -0.18
    åIJįä¹ī
    -0.18
    ,callback
    -0.18
    POSITIVE LOGITS
    ä¸İåIJ¦
    0.49
    åIJ¦
    0.44
     bool
    0.44
    bool
    0.39
    .bool
    0.39
     true
    0.38
     false
    0.38
    å¸ĥå°Ķ
    0.38
     boolean
    0.38
     yes
    0.38
    Activations Density 1.552%

    No Known Activations