© 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. 620
    Prev
    Next
    INDEX
    Explanations

    names and entities

    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
    geries
    -0.28
    ].'
    -0.25
     )[
    -0.24
    .§
    -0.22
    ðŁļ«
    -0.22
    ,No
    -0.21
    )!↵
    -0.20
    ลาย
    -0.20
    --------------↵
    -0.20
    ...";↵
    -0.20
    POSITIVE LOGITS
     PartialView
    0.22
     Trib
    0.22
     trib
    0.20
    ério
    0.20
    legg
    0.19
    rganization
    0.19
    ancybox
    0.19
    Wunused
    0.18
    ideos
    0.18
    toa
    0.18
    Activations Density 0.010%

    No Known Activations