© 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. 2787
    Prev
    Next
    INDEX
    Explanations

    Complex specific topics

    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
    igin
    -0.23
    UPI
    -0.20
    âİŀ
    -0.20
     Raz
    -0.20
     dudes
    -0.20
     getService
    -0.20
    judul
    -0.19
    å½ĵåľ°æĶ¿åºľ
    -0.19
     øns
    -0.19
    UNIX
    -0.19
    POSITIVE LOGITS
     IonicPage
    0.29
    isphere
    0.26
    akest
    0.24
    çıº
    0.21
    rapped
    0.21
    ffield
    0.20
    ANDOM
    0.20
    (nullable
    0.20
    .CustomButton
    0.19
    #ab
    0.19
    Activations Density 0.001%

    No Known Activations