© 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. 2410
    Prev
    Next
    INDEX
    Explanations

    technical or academic

    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
    Tambah
    -0.22
    SSFWorkbook
    -0.21
    å¿ħ
    -0.21
    GLOBALS
    -0.20
    å®Į
    -0.19
     Gan
    -0.19
    lass
    -0.19
    为人
    -0.18
    ewidth
    -0.18
    å¾Ń
    -0.18
    POSITIVE LOGITS
    ormsg
    0.24
    å¿«ä¸ī
    0.23
    ìĤŃ
    0.22
    çļĦ带é¢Ĩ
    0.22
     fkk
    0.21
     avalia
    0.21
    /Dk
    0.21
    å¿ĥ仪
    0.20
    .getElementsByName
    0.20
     çĶŁåij½åij¨æľŁ
    0.20
    Activations Density 0.001%

    No Known Activations