© 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. 2127
    Prev
    Next
    INDEX
    Explanations

    if statement

    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
    .apiUrl
    -0.24
    irlines
    -0.20
    èĩĬ
    -0.20
    FlatButton
    -0.20
    ormsg
    -0.20
    å°±ç»Ļ大家
    -0.20
     Rigidbody
    -0.20
    linkplain
    -0.19
    ronym
    -0.19
    æĢ§è´¨
    -0.19
    POSITIVE LOGITS
     if
    0.22
    if
    0.22
    /if
    0.22
     BLL
    0.21
    .if
    0.21
    å¦Ĥæŀľ
    0.20
    åĹĴ
    0.20
     å¦Ĥæŀľ
    0.19
    iết
    0.19
    é¥
    0.19
    Activations Density 0.138%

    No Known Activations