© 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. 2076
    Prev
    Next
    INDEX
    Explanations

    subtract

    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
    .baomidou
    -0.23
    onomies
    -0.23
    imid
    -0.21
    noDB
    -0.21
     piger
    -0.20
    InterfaceOrientation
    -0.20
    .DeserializeObject
    -0.19
    íĶĦë¡ľê·¸
    -0.19
    ãĤ·ãĥ³ãĥĹ
    -0.19
    :'.$
    -0.19
    POSITIVE LOGITS
     subtract
    0.41
    subtract
    0.41
     difference
    0.41
     Difference
    0.38
    difference
    0.36
     Subtract
    0.36
     subtraction
    0.35
    å·®å¼Ĥ
    0.35
    Difference
    0.34
     differences
    0.31
    Activations Density 0.049%

    No Known Activations