© 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. 1866
    Prev
    Next
    INDEX
    Explanations

    random snippets

    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
    åŃIJ
    -0.28
    tober
    -0.27
    mue
    -0.26
    vê
    -0.26
    chestra
    -0.26
    ventario
    -0.25
    ï¸ı
    -0.25
    \brief
    -0.24
    åŃIJéĩĮ
    -0.24
    redients
    -0.24
    POSITIVE LOGITS
    à§įà¦
    0.39
    à¯įà®
    0.36
    à¥įà¤
    0.33
    åĬĽè¿ĺæĺ¯
    0.31
    çĪ·
    0.30
    .SingleOrDefault
    0.27
    íŀĪ
    0.27
    ley
    0.27
    å§ĭ建
    0.26
    NESS
    0.26
    Activations Density 4.376%

    No Known Activations