© 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. 3021
    Prev
    Next
    INDEX
    Explanations

    labels or names

    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
    rotch
    -0.23
    èģ±
    -0.21
    olicited
    -0.21
    nea
    -0.20
    bsolute
    -0.20
    MeshPro
    -0.20
    iscrimination
    -0.20
    >{"
    -0.20
     heightFor
    -0.19
    lke
    -0.19
    POSITIVE LOGITS
    ãİĿ
    0.24
    -'.$
    0.20
    herits
    0.19
    prs
    0.19
    _KeyPress
    0.19
    umbed
    0.19
    å¤ļç§įå½¢å¼ı
    0.18
    æ¬ł
    0.18
    CharArray
    0.18
    iland
    0.18
    Activations Density 0.005%

    No Known Activations