© 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. 3198
    Prev
    Next
    INDEX
    Explanations

    math expression syntax

    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
     newcom
    -0.31
    alborg
    -0.28
    â¬ĩ
    -0.27
    âĹĢ
    -0.25
    ,No
    -0.25
    对åħ¶çľŁå®ŀ
    -0.25
    eus
    -0.24
    arhus
    -0.24
    âľķ
    -0.24
    byss
    -0.24
    POSITIVE LOGITS
    2
    0.24
    带
    0.22
    é©°
    0.21
    иÑģк
    0.20
    ä¼ļå¼ķèµ·
    0.20
    PushMatrix
    0.19
    ä»£æĽ¿
    0.19
    ress
    0.19
     Pas
    0.19
    1
    0.19
    Activations Density 0.011%

    No Known Activations