© 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. 2674
    Prev
    Next
    INDEX
    Explanations

    technical or code symbols

    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
    æīĭèĦļ
    -0.22
    æīĢæıIJä¾Ľ
    -0.20
    ä¼Ĭæĭī
    -0.20
     novitÃł
    -0.20
    oggler
    -0.20
     Wonderland
    -0.19
    åħ¬å¼Ģ课
    -0.19
    öyle
    -0.19
    itage
    -0.18
    身åŃIJ
    -0.18
    POSITIVE LOGITS
    efined
    0.24
    weed
    0.23
    itals
    0.22
    quate
    0.21
    porate
    0.21
    #ac
    0.21
     Baghd
    0.20
    irlines
    0.20
    (@"%@",
    0.20
    "sync
    0.20
    Activations Density 0.014%

    No Known Activations