© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2926
    Prev
    Next
    INDEX
    Explanations

    copyright and license

    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
    -With
    -0.22
    )init
    -0.22
    :".$
    -0.21
     ?");↵
    -0.21
    /filepath
    -0.20
    ILER
    -0.20
    iale
    -0.20
    ï¹¢
    -0.20
    줬
    -0.20
    .TextAlign
    -0.19
    POSITIVE LOGITS
    entiful
    0.22
    ytt
    0.21
     meddling
    0.20
    conti
    0.19
    berapa
    0.19
    ripper
    0.19
    contri
    0.19
    æ¯Ľ
    0.18
    åĨĪ
    0.18
    vertise
    0.18
    Activations Density 1.002%

    No Known Activations