© 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. 494
    Prev
    Next
    INDEX
    Explanations

    Author identifiers

    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
    noinspection
    -0.27
     */č↵č↵č↵
    -0.25
    SSERT
    -0.24
    å°±ç»Ļ大家
    -0.22
    MMC
    -0.22
     CGRectGet
    -0.22
     cioè
    -0.22
    ,{"
    -0.22
    />.
    -0.21
    ATAB
    -0.21
    POSITIVE LOGITS
    ↵
    0.22
    umblr
    0.21
    inctions
    0.20
    inbox
    0.19
     _
    0.19
    edicine
    0.19
    mojom
    0.19
    heim
    0.19
    ,
    0.19
     newPos
    0.19
    Activations Density 0.234%

    No Known Activations