© 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. 550
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    alborg
    -0.21
    chu
    -0.21
    èģ©
    -0.21
    dür
    -0.20
    _refl
    -0.20
    crast
    -0.20
    paralleled
    -0.20
    ///č↵
    -0.19
    :maj
    -0.19
    -Americ
    -0.19
    POSITIVE LOGITS
    rawtypes
    0.23
    'gc
    0.20
    anitize
    0.19
     IllegalAccessException
    0.19
    Calibri
    0.19
    memberOf
    0.19
    OutOfBounds
    0.19
    æķĿ
    0.19
    ulumi
    0.18
    ä¸įå¼Ģ
    0.18
    Activations Density 0.010%

    No Known Activations