© 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. 2702
    Prev
    Next
    INDEX
    Explanations

    numerical thresholds

    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
    .Ticks
    -0.20
    önü
    -0.20
    èµį
    -0.20
    ?('
    -0.19
     {č↵č↵č↵
    -0.19
    å¤§åĽ½
    -0.19
    hế
    -0.18
     ]);
    -0.18
    (sort
    -0.18
    _dispatcher
    -0.18
    POSITIVE LOGITS
    èĩ³å°ij
    0.47
    ä¸įä½İäºİ
    0.36
    ä¸įå°ijäºİ
    0.35
    èµ·çłģ
    0.33
    è¶ħè¿ĩ
    0.32
     âī¥
    0.28
    è¿ŀç»Ń
    0.28
     ÑħоÑĤÑı
    0.28
    âī§
    0.27
    年以ä¸Ĭ
    0.27
    Activations Density 0.490%

    No Known Activations