© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3201
    Prev
    Next
    INDEX
    Explanations

    grants and resources

    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
     IonicPage
    -0.24
    toJson
    -0.22
     AppBundle
    -0.22
     Dort
    -0.21
     ArtÃŃculo
    -0.21
    pard
    -0.21
     COPYING
    -0.20
    å£ħ
    -0.20
    ESSAGES
    -0.19
    è·Ĺ
    -0.19
    POSITIVE LOGITS
    åĩºèĩª
    0.26
    éļ¶å±ŀäºİ
    0.25
    å¾ķ
    0.23
    .chomp
    0.23
     belonging
    0.23
     thuá»Ļc
    0.22
     ضÙħÙĨ
    0.22
    /www
    0.21
    åºĭ
    0.21
     bab
    0.20
    Activations Density 1.734%

    No Known Activations