© 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. 1119
    Prev
    Next
    INDEX
    Explanations

    technical systems and concepts

    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
    ecided
    -0.27
    åıµ
    -0.24
    iasco
    -0.20
    rir
    -0.20
    fortunate
    -0.19
    _secs
    -0.19
    ouched
    -0.18
    âı³
    -0.18
    CAPE
    -0.18
    游æĪıæĬĢå·§
    -0.18
    POSITIVE LOGITS
    rchive
    0.24
    timeofday
    0.21
    .GroupLayout
    0.21
     août
    0.20
    reation
    0.20
    abis
    0.20
    nyder
    0.19
    qrst
    0.19
     Kardash
    0.19
    //↵↵↵
    0.19
    Activations Density 10.650%

    No Known Activations