© 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. 3385
    Prev
    Next
    INDEX
    Explanations

    select

    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
     libertin
    -0.26
     oppon
    -0.24
     consc
    -0.24
    dbContext
    -0.23
    GetPosition
    -0.23
     decide
    -0.22
     categorie
    -0.21
    ãģijãģ°
    -0.21
     resultat
    -0.21
    objectManager
    -0.20
    POSITIVE LOGITS
    (*)(
    0.30
    /Dk
    0.28
     обÑĢаÑīа
    0.26
    herits
    0.25
    ocaly
    0.23
    استÙĤÙĦ
    0.22
    },{↵
    0.22
    NCY
    0.22
     (*)(
    0.22
    ksam
    0.21
    Activations Density 0.089%

    No Known Activations