© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 943
    Prev
    Next
    INDEX
    Explanations

    common topics

    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
    ?"↵↵↵↵
    -0.32
    /Dk
    -0.30
    -With
    -0.29
     ÑģенÑĤ
    -0.28
    alties
    -0.26
    âĸ¹
    -0.26
    .)↵↵↵↵
    -0.26
    -Trump
    -0.26
     bigot
    -0.26
     yarg
    -0.25
    POSITIVE LOGITS
        		↵
    0.25
     **
    0.25
    éľĵ
    0.22
    ĪæĿĥ
    0.21
    姮
    0.21
    羣æŃ£åģļåĪ°
    0.21
    /fontawesome
    0.20
    WebResponse
    0.20
    欢è¿İ大家
    0.20
    ><?=$
    0.20
    Activations Density 0.861%

    No Known Activations