© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 681
    Prev
    Next
    INDEX
    Explanations

    proper / appropriate

    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
     èĩªåĬ¨çĶŁæĪIJ
    -0.24
    个å¤ļå°ıæŶ
    -0.21
     идеалÑĮн
    -0.21
    .shiro
    -0.21
    .endTime
    -0.21
     potrÃł
    -0.21
    /MIT
    -0.20
    нÑıÑĤие
    -0.20
    leftright
    -0.20
    stery
    -0.20
    POSITIVE LOGITS
    è¶³å¤Ł
    0.42
    å°½åı¯èĥ½
    0.39
    èĩ³å°ij
    0.39
     proper
    0.38
    è¶³å¤ŁçļĦ
    0.35
     appropriate
    0.34
    èµ·çłģ
    0.34
     properly
    0.33
     ÑħоÑĤÑı
    0.33
    ä¸įä½İäºİ
    0.33
    Activations Density 5.492%

    No Known Activations