© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2658
    Prev
    Next
    INDEX
    Explanations

    to be verbs

    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
    /Gate
    -0.32
    '&&
    -0.26
    );">↵
    -0.26
    /Branch
    -0.25
    ertoire
    -0.25
     fkk
    -0.24
    usercontent
    -0.24
    {@
    -0.24
     ?>↵↵↵
    -0.23
    ?>>
    -0.23
    POSITIVE LOGITS
    åĵ¨
    0.23
     xhttp
    0.20
    åľ¨è¿Ļ
    0.19
     sideline
    0.19
     freelancer
    0.19
    ed
    0.19
     precisely
    0.19
    ä¸Ģå°ģä¿¡
    0.18
     emblem
    0.18
     this
    0.18
    Activations Density 0.173%

    No Known Activations