© 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. 4340
    Prev
    Next
    INDEX
    Explanations

    Technical or specific names

    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
    :".$
    -0.24
    ksam
    -0.23
    .dtd
    -0.23
    /XMLSchema
    -0.21
    /gin
    -0.21
    çݩ家æľĭåıĭ
    -0.21
    jsc
    -0.21
    .gf
    -0.20
    /Branch
    -0.20
    iếu
    -0.20
    POSITIVE LOGITS
     vmax
    0.21
    æĦı大
    0.18
    RoutingModule
    0.18
    çĭ¼
    0.18
    htag
    0.18
     beyond
    0.18
     Posté
    0.18
    è¦ģæĬĬ
    0.18
    ace
    0.17
    (EXIT
    0.17
    Activations Density 0.003%

    No Known Activations