© 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. 1259
    Prev
    Next
    INDEX
    Explanations

    Technical questions

    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
    æľīçļĦçݩ家
    -0.33
    chestra
    -0.27
     ?>↵↵↵
    -0.26
    ";//
    -0.25
    "testing
    -0.25
    *)_
    -0.24
    绺
    -0.23
    benh
    -0.23
     realtime
    -0.23
    {!!
    -0.22
    POSITIVE LOGITS
    -toast
    0.28
     èĭ¥è¦ģ
    0.28
     disappe
    0.27
    .CompareTag
    0.26
    缸è¾ĥäºİ
    0.26
     datings
    0.25
     \(
    0.25
    éĢĨè¢Ń
    0.25
    $MESS
    0.24
     bigot
    0.23
    Activations Density 4.138%

    No Known Activations