© 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. 3479
    Prev
    Next
    INDEX
    Explanations

    total

    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
    ..<
    -0.25
    -Cs
    -0.24
    );↵↵↵↵↵
    -0.24
    :NO
    -0.23
    mmo
    -0.23
     délai
    -0.22
     +=↵
    -0.22
    ICTURE
    -0.22
    DOG
    -0.22
    )||(
    -0.21
    POSITIVE LOGITS
    æĢ»è®¡
    0.51
    åIJĪ计
    0.48
     total
    0.44
     Total
    0.42
    åħ±è®¡
    0.42
     Tot
    0.38
     tot
    0.37
     TOTAL
    0.37
    TOTAL
    0.36
    Total
    0.36
    Activations Density 0.029%

    No Known Activations