© 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. 2931
    Prev
    Next
    INDEX
    Explanations

    statistical interaction

    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
    uments
    -0.25
     gap
    -0.20
    ors
    -0.19
    0
    -0.19
    1
    -0.19
    5
    -0.19
    opia
    -0.18
    å°ijå¹´
    -0.18
    8
    -0.18
    LinkId
    -0.18
    POSITIVE LOGITS
    <?=$
    0.26
    interaction
    0.24
    ï¼ģ",
    0.24
     Interaction
    0.24
    Interaction
    0.24
     interaction
    0.24
    Xã
    0.24
    intérêt
    0.24
    æķĪæŀľ
    0.23
    .MONTH
    0.23
    Activations Density 0.067%

    No Known Activations