© 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. 1560
    Prev
    Next
    INDEX
    Explanations

    ãĢģ

    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
     pestic
    -0.24
    );$
    -0.24
    byss
    -0.22
    Īëĭ¤
    -0.22
     "()
    -0.22
    -await
    -0.22
    }});↵
    -0.22
    ãģ¦ãģĬãĤĬ
    -0.22
    ãģĤãĤĭãģĦ
    -0.21
     numel
    -0.21
    POSITIVE LOGITS
    ãĢģ
    0.79
    ,
    0.44
    ､
    0.42
    ãĢģ“
    0.40
    ãĢģãĢģ
    0.37
    ãĢģ↵↵
    0.35
    ãĢģãĢĮ
    0.34
    -,
    0.28
    åļĨ
    0.25
    ï¼Į
    0.24
    Activations Density 3.374%

    No Known Activations