© 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. 2764
    Prev
    Next
    INDEX
    Explanations

    any

    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
     Noticed
    -0.29
     SharedModule
    -0.27
    URLException
    -0.26
     Decorating
    -0.26
     MatSnackBar
    -0.25
    ::$_
    -0.24
     ÅĽwiadom
    -0.24
     Ãĸnceki
    -0.24
    ilogy
    -0.24
    'icon
    -0.24
    POSITIVE LOGITS
     readdir
    0.23
    ç³ĸå°¿
    0.21
     LinearGradient
    0.20
     vidé
    0.20
     squirt
    0.19
    ç«¿
    0.18
     resend
    0.18
    ResourceManager
    0.18
     mz
    0.18
     tablesp
    0.18
    Activations Density 0.132%

    No Known Activations