© 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. 1182
    Prev
    Next
    INDEX
    Explanations

    technical and legal

    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
    (UIAlertAction
    -0.22
     DirectoryInfo
    -0.19
     Warcraft
    -0.18
     Trafford
    -0.18
     Bec
    -0.18
    ORIZONTAL
    -0.17
    è¸ŀ
    -0.17
    _KeyDown
    -0.17
    -Origin
    -0.17
     antibiot
    -0.17
    POSITIVE LOGITS
    .RelativeLayout
    0.25
    对çħ§æ£ĢæŁ¥
    0.24
    .Disclaimer
    0.22
    /Dk
    0.21
    _pemb
    0.21
    íķĺìĺĢìĬµëĭĪëĭ¤
    0.21
    vanished
    0.21
    顾
    0.20
    åįĥä¼ı
    0.20
    âĦł
    0.19
    Activations Density 0.244%

    No Known Activations