© 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. 928
    Prev
    Next
    INDEX
    Explanations

    our, ourselves

    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
     itself
    -0.27
    ãĢĤwww
    -0.25
    è·ŁæĪij说
    -0.24
    ï¼ģ');↵
    -0.23
    æľ¬äºº
    -0.22
    ******č↵
    -0.22
    æľ¬åĽ½
    -0.21
    empt
    -0.21
    _us
    -0.21
    ¡´
    -0.21
    POSITIVE LOGITS
     ourselves
    0.79
    åĽłä¸ºæĪij们
    0.40
    Ñħодим
    0.38
     our
    0.35
    æĪij们çļĦ
    0.34
    ä½ĨæĪij们
    0.32
    å½ĵæĪij们
    0.31
    à¸Ĥà¸Ńà¸ĩà¹Ģรา
    0.28
    å¦ĤæŀľæĪij们
    0.28
     наÑĪиÑħ
    0.27
    Activations Density 1.647%

    No Known Activations