© 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. 1743
    Prev
    Next
    INDEX
    Explanations

    Conclusion

    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
    çĶ±äºİ
    -0.31
    åĽłä¸ºæĪij
    -0.30
    åĽłä¸º
    -0.29
    åĽłä¸ºæĪij们
    -0.27
    çĶ±æĸ¼
    -0.26
    åĽłä¸ºåľ¨
    -0.26
     debido
    -0.25
    åĽłçĤº
    -0.24
    çķ¢ç«Ł
    -0.24
    âĪµ
    -0.23
    POSITIVE LOGITS
    ä¹Łå°±
    0.40
    åıªå¥½
    0.30
    å¿ħçĦ¶
    0.30
    éļ¾æĢª
    0.29
     accordingly
    0.28
    便
    0.27
    forth
    0.26
     conclude
    0.26
    ä¸įå¾Ĺä¸į
    0.26
    å°±æľīäºĨ
    0.25
    Activations Density 1.989%

    No Known Activations