© 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. 4148
    Prev
    Next
    INDEX
    Explanations

    section identifiers

    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
    igham
    -0.24
    mour
    -0.20
    çIJ®
    -0.20
    mj
    -0.19
    ting
    -0.19
    ·»
    -0.19
    olicit
    -0.19
    ISTS
    -0.18
    åıĮåįģä¸Ģ
    -0.18
    .AsyncTask
    -0.18
    POSITIVE LOGITS
    ","\
    0.27
    readcr
    0.24
     addCriterion
    0.23
    lobber
    0.22
    .heroku
    0.22
    çī¹èī²ç¤¾ä¼ļ
    0.22
    usercontent
    0.22
    lete
    0.21
    iferay
    0.21
    ".↵↵↵↵
    0.21
    Activations Density 0.005%

    No Known Activations