© 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. 49
    Prev
    Next
    INDEX
    Explanations

    which

    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
    ãĢģ
    -0.24
    1
    -0.23
    4
    -0.23
     gridColumn
    -0.23
     isize
    -0.22
     antlr
    -0.22
    3
    -0.21
    DivElement
    -0.21
    2
    -0.20
     ++$
    -0.20
    POSITIVE LOGITS
    upon
    0.30
    rippling
    0.28
    ='<?
    0.27
     èĭ¥è¦ģ
    0.27
    úsqueda
    0.27
    ,Th
    0.24
    ówi
    0.24
    }'",
    0.24
    ä¸ĭéĿ¢æĺ¯å°ı
    0.24
    "./
    0.24
    Activations Density 1.196%

    No Known Activations