© 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. 2984
    Prev
    Next
    INDEX
    Explanations

    specific details

    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
     ViewChild
    -0.21
    metros
    -0.19
     modele
    -0.19
    è®Ń
    -0.19
    ï¼Īç¬ij
    -0.18
     inval
    -0.18
    ëŁ¼
    -0.18
    iores
    -0.18
    esis
    -0.18
    );;↵
    -0.18
    POSITIVE LOGITS
    VERRIDE
    0.29
    oriously
    0.24
    /Internal
    0.23
     ×Ķ×ķ×ĵ
    0.23
    CCCCCC
    0.22
    ëĵ¦
    0.21
    (jQuery
    0.21
    ThanOr
    0.21
    ourmet
    0.20
    loquent
    0.20
    Activations Density 0.006%

    No Known Activations