© 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. 1644
    Prev
    Next
    INDEX
    Explanations

    legal and code context

    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
     Decompiled
    -0.26
    çĩķ
    -0.22
    ç®IJ
    -0.20
    åĨħéĺģ
    -0.20
    æīĢå¾Ĺç¨İ
    -0.20
    RLF
    -0.19
    ÙħسابÙĤØ©
    -0.19
     RaisePropertyChanged
    -0.19
    个å¤ļå°ıæŶ
    -0.19
     Crushers
    -0.18
    POSITIVE LOGITS
    ("$.
    0.25
    ahoma
    0.23
     onCreateView
    0.22
    arseille
    0.22
    lyph
    0.20
    AMILY
    0.20
    ugeot
    0.20
    )))),
    0.20
     makeStyles
    0.20
    .tex
    0.20
    Activations Density 4.369%

    No Known Activations