© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4324
    Prev
    Next
    INDEX
    Explanations

    citations and references

    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
    Negative Logits
     various
    -0.23
    åIJĦåįķä½į
    -0.21
     etc
    -0.21
     standard
    -0.20
    æłĩåĩĨ
    -0.20
    Mixin
    -0.20
    ,
    -0.19
    présent
    -0.19
    åIJĦ级
    -0.19
    ç¼Ĺ
    -0.19
    POSITIVE LOGITS
     Erectile
    0.28
    /Instruction
    0.27
    èĴ¡
    0.26
     èĭ¥è¦ģ
    0.26
    âļĹ
    0.25
    âĮĤ
    0.24
    /↵↵↵↵
    0.24
     Depths
    0.24
    ðŁĵIJ
    0.24
    )||(
    0.23
    Activations Density 0.028%

    No Known Activations