© 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. 3919
    Prev
    Next
    INDEX
    Explanations

    code elements

    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
    %X
    -0.24
    bellion
    -0.23
     får
    -0.23
    prowad
    -0.20
    ditor
    -0.20
    ulerAngles
    -0.20
    å¹ħ度
    -0.20
    BackStack
    -0.20
    esub
    -0.20
    .shows
    -0.19
    POSITIVE LOGITS
    ().'/
    0.22
    ousedown
    0.21
     avalia
    0.20
    ĮĢ
    0.20
    ç»Ħéķ¿
    0.19
    .UseVisualStyleBackColor
    0.18
    åŁ¹è®ŃçıŃ
    0.18
     startPoint
    0.18
     ?>↵↵↵
    0.18
    earn
    0.18
    Activations Density 0.001%

    No Known Activations