© 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. 3810
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    postalcode
    -0.21
    åĵĤ
    -0.21
     IDb
    -0.20
    ãİŀ
    -0.20
    Getty
    -0.20
    maids
    -0.20
    pire
    -0.19
    TIMER
    -0.19
    ","","
    -0.19
     GUIStyle
    -0.19
    POSITIVE LOGITS
     Jr
    0.45
     Inc
    0.33
    Inc
    0.29
     jr
    0.25
     III
    0.24
     INC
    0.24
     II
    0.24
    INC
    0.23
    âħ
    0.23
    inc
    0.22
    Activations Density 0.340%

    No Known Activations