© 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. 3622
    Prev
    Next
    INDEX
    Explanations

    therefore thus

    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
     therefore
    -0.43
    åĽłæѤ
    -0.39
     thus
    -0.32
    Therefore
    -0.30
     donc
    -0.30
    äºİæĺ¯
    -0.28
     daher
    -0.27
     Therefore
    -0.27
     hence
    -0.27
    thus
    -0.27
    POSITIVE LOGITS
    -overlay
    0.24
    rtle
    0.23
     ?>↵↵↵
    0.22
        ↵    ↵    ↵    ↵
    0.22
    íĶĦë¡ľê·¸
    0.21
     TORT
    0.21
    âĹĢ
    0.21
     boobs
    0.21
     dicks
    0.21
     bénéficie
    0.20
    Activations Density 0.042%

    No Known Activations