© 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. 2519
    Prev
    Next
    INDEX
    Explanations

    change of status

    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
    ðŁķij
    -0.28
    ,");↵
    -0.25
    )./
    -0.25
    .nlm
    -0.25
    -UA
    -0.24
    иÑĢÑĥÑİÑī
    -0.23
    OrNil
    -0.23
    )))),
    -0.23
    hế
    -0.23
    icaid
    -0.23
    POSITIVE LOGITS
    æĽ´åIJį为
    0.51
     renamed
    0.47
    åīį身
    0.37
     rename
    0.36
     renaming
    0.35
     merged
    0.34
    çİ°åľ¨çļĦ
    0.33
    åIJĪ并
    0.33
     predecessor
    0.33
    formerly
    0.32
    Activations Density 0.887%

    No Known Activations