© 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. 2184
    Prev
    Next
    INDEX
    Explanations

    technical code

    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
    女ãģ®
    -0.21
    å¹´ä¹ĭä¹ħ
    -0.20
     tet
    -0.19
    å¾Ń
    -0.19
    çŁį
    -0.18
    @PostMapping
    -0.18
    é¢Ģ
    -0.18
    åIJ¦
    -0.18
     Airways
    -0.18
     ningu
    -0.17
    POSITIVE LOGITS
    mouseleave
    0.23
    :numel
    0.22
    oldt
    0.21
    ::::::::
    0.21
    .Formatter
    0.21
    yscale
    0.21
    /tos
    0.21
    ;set
    0.20
    ]={↵
    0.20
    ledged
    0.20
    Activations Density 0.002%

    No Known Activations