© 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. 2469
    Prev
    Next
    INDEX
    Explanations

    contrast concession

    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
     ?>↵↵↵
    -0.23
     zwar
    -0.23
     btw
    -0.21
    çĤ·
    -0.21
    ãģ¾ãģĹãģŁãģĮ
    -0.20
    èĻ½çĦ¶
    -0.20
    éĽĸ
    -0.20
    ãĤĤãģ¡ãĤį
    -0.20
    _nama
    -0.19
    ","+
    -0.19
    POSITIVE LOGITS
     nonetheless
    0.45
     nevertheless
    0.41
    è¿ĺæĺ¯è¦ģ
    0.33
    åį´æĺ¯
    0.33
    è¿ĺæĺ¯
    0.31
    æĪijè¿ĺæĺ¯
    0.28
    åį´
    0.27
    è¿ĺæĺ¯ä¼ļ
    0.27
    åIJĮæĹ¶ä¹Ł
    0.26
     trotz
    0.25
    Activations Density 1.192%

    No Known Activations