© 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. 3702
    Prev
    Next
    INDEX
    Explanations

    0

    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
     GdaÅĦsk
    -0.28
    scrição
    -0.28
    ltra
    -0.28
     Fired
    -0.27
    ----</
    -0.26
    abox
    -0.26
    alink
    -0.26
     Decorating
    -0.26
    ¡´
    -0.25
    etrain
    -0.25
    POSITIVE LOGITS
     boobs
    0.25
     acompaña
    0.23
     taraf
    0.22
     protester
    0.21
     entidad
    0.21
    wegian
    0.21
    åĬłå·¥åİĤ
    0.21
    ForRow
    0.21
     licensors
    0.20
     panties
    0.20
    Activations Density 0.195%

    No Known Activations