© 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. 3910
    Prev
    Next
    INDEX
    Explanations

    math operators

    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
     LENG
    -0.21
    çIJĨäºĭä¼ļ
    -0.20
    thinkable
    -0.20
    leanor
    -0.20
    æ·Ħ
    -0.20
    erial
    -0.19
    lijah
    -0.19
    APS
    -0.18
     Mort
    -0.18
    ahas
    -0.18
    POSITIVE LOGITS
    $MESS
    0.21
    ÉĴ
    0.20
    \grid
    0.20
    'order
    0.20
     sluts
    0.19
    nett
    0.19
    volução
    0.19
     HeaderComponent
    0.18
    -application
    0.18
     bordel
    0.18
    Activations Density 0.081%

    No Known Activations