© 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. 87
    Prev
    Next
    INDEX
    Explanations

    begin or continue

    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
     currently
    -0.34
    缮åīį
    -0.34
     recent
    -0.33
    å½ĵä¸ĭ
    -0.29
    äºĭåħĪ
    -0.28
    å½ĵæŶ
    -0.27
    è¿ijæľŁ
    -0.27
    currently
    -0.26
     today
    -0.26
    å½ĵåīį
    -0.26
    POSITIVE LOGITS
    æŃ£å¼ı
    0.44
    å¼Ģå§ĭ
    0.42
     begins
    0.38
     begin
    0.37
     finally
    0.35
     began
    0.35
    ä¹Łå¼Ģå§ĭ
    0.34
    ä¸įåĨįæĺ¯
    0.33
     become
    0.32
     officially
    0.32
    Activations Density 4.595%

    No Known Activations