© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 130
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
     enthus
    -0.30
     maduras
    -0.29
     sigu
    -0.27
     rencont
    -0.27
    بسÙĬØ·
    -0.26
     acompaña
    -0.26
     prostitu
    -0.26
     fierc
    -0.25
     charisma
    -0.24
     développe
    -0.24
    POSITIVE LOGITS
     nonatomic
    0.32
    ðŁļ©
    0.29
    ImageButton
    0.28
    سبÙĪع
    0.27
    .tintColor
    0.27
    èĦĺ
    0.27
    mue
    0.26
    suming
    0.26
    詹å§Ĩ
    0.25
    å§Ķåī¯ä¹¦è®°
    0.25
    Activations Density 11.057%

    No Known Activations