© 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. 1117
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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
    -scenes
    -0.28
    	assertNotNull
    -0.21
    .MouseDown
    -0.21
     migrationBuilder
    -0.20
    twor
    -0.20
    åı¹äºĨ
    -0.20
    .PropTypes
    -0.20
     tô
    -0.19
    HostException
    -0.19
    serter
    -0.19
    POSITIVE LOGITS
    addPreferredGap
    0.28
    br
    0.22
    éĩįè¦ģ举æݪ
    0.22
    utterstock
    0.21
    toFloat
    0.21
     endl
    0.21
    .sep
    0.21
    ãİı
    0.20
    isRequired
    0.20
     ".
    0.20
    Activations Density 0.539%

    No Known Activations