© 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. 2576
    Prev
    Next
    INDEX
    Explanations

    getting worse

    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
    ä¸įçĶĺ
    -0.23
    rze
    -0.23
    tered
    -0.21
    infer
    -0.21
    %",↵
    -0.21
    isu
    -0.20
     CommonModule
    -0.20
     FactoryBot
    -0.20
    /command
    -0.19
    ámara
    -0.19
    POSITIVE LOGITS
    åıįèĢĮ
    0.66
    åıįåĢĴ
    0.46
     ìĺ¤íŀĪ볤
    0.44
    åıªä¼ļ
    0.43
    缸åıį
    0.41
    æģ°æģ°
    0.34
     worse
    0.30
    ãģ©ãģĵãĤį
    0.29
    è¿Ľä¸ĢæŃ¥
    0.29
    обоÑĢоÑĤ
    0.29
    Activations Density 0.378%

    No Known Activations