© 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. 1920
    Prev
    Next
    INDEX
    Explanations

    failure or lack

    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
    /Runtime
    -0.25
    ]bool
    -0.24
    меÑĩа
    -0.22
    ######↵
    -0.22
    antino
    -0.22
    ."&
    -0.21
    'icon
    -0.21
    #######↵
    -0.21
    onnen
    -0.21
    "description
    -0.21
    POSITIVE LOGITS
     altogether
    0.31
     due
    0.29
    due
    0.29
    åºĶæľīçļĦ
    0.27
    =$('#
    0.26
     attempts
    0.25
     debido
    0.23
    çĶ±äºİ
    0.23
    çĶļèĩ³
    0.23
    太å¤ļçļĦ
    0.23
    Activations Density 3.235%

    No Known Activations