© 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. 1091
    Prev
    Next
    INDEX
    Explanations

    but

    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
     zwar
    -0.36
    èĻ½çĦ¶
    -0.33
    åĽºçĦ¶
    -0.31
    èĻ½
    -0.28
    èĻ½è¯´
    -0.28
    åı¯æĺ¯
    -0.26
     therefore
    -0.25
    æĢ§ä»·
    -0.25
     though
    -0.23
    à¹ģà¸ķ
    -0.23
    POSITIVE LOGITS
     nevertheless
    0.42
    chers
    0.41
     nonetheless
    0.40
    chedulers
    0.34
    åIJĮæĹ¶ä¹Ł
    0.32
    lers
    0.28
    ler
    0.28
    åį´æĺ¯
    0.27
     toch
    0.26
    declaring
    0.25
    Activations Density 1.360%

    No Known Activations