© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1727
    Prev
    Next
    INDEX
    Explanations

    word fragments

    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
    设计åĻ¨
    -0.27
    :<?
    -0.25
    ç¡ķ士çłĶ究
    -0.25
    ðŁijĨ
    -0.24
    íĶĦë¡ľê·¸
    -0.24
    byss
    -0.23
    .BASELINE
    -0.23
    åĭł
    -0.22
    (OP
    -0.22
    xec
    -0.22
    POSITIVE LOGITS
    0.26
    impse
    0.24
    berra
    0.24
    -scalable
    0.23
    alie
    0.22
     neighb
    0.20
     troch
    0.20
    ippines
    0.19
     undone
    0.19
     licensee
    0.19
    Activations Density 0.220%

    No Known Activations