© 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. 3391
    Prev
    Next
    INDEX
    Explanations

    licensing details

    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
    趿
    -0.23
    forgettable
    -0.22
    ä¼ļä¼ļéķ¿
    -0.22
    æĹłéļľç¢į
    -0.21
    Ëī
    -0.21
    __);
    -0.21
    æĭľå¸ĪåѦ
    -0.19
     yans
    -0.19
    precedented
    -0.19
    paralleled
    -0.19
    POSITIVE LOGITS
     wur
    0.20
    bsite
    0.20
     ÙĬÙĪس
    0.20
    inson
    0.20
    ouri
    0.19
    rophe
    0.19
    ç²ī
    0.19
     MSM
    0.18
     dataIndex
    0.18
    ays
    0.18
    Activations Density 0.001%

    No Known Activations