© 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. 1017
    Prev
    Next
    INDEX
    Explanations

    pone

    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
    -initialized
    -0.21
    regunta
    -0.21
    BAB
    -0.20
    setBackground
    -0.19
    >').
    -0.19
    æºı
    -0.19
    igham
    -0.19
    CREMENT
    -0.19
    observeOn
    -0.19
    å°±ç»Ļ大家
    -0.19
    POSITIVE LOGITS
    ChildIndex
    0.24
    puties
    0.23
    puty
    0.20
    âĩIJ
    0.20
    isSelected
    0.20
    pone
    0.20
    ưỡ
    0.19
    ergency
    0.19
    红楼
    0.19
    }><
    0.18
    Activations Density 0.008%

    No Known Activations