© 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. 3830
    Prev
    Next
    INDEX
    Explanations

    scientific technical 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
    ighbor
    -0.20
    èħļ
    -0.19
    usty
    -0.19
    æ²Ĩ
    -0.19
    ecera
    -0.18
    çłľ
    -0.18
    uccess
    -0.18
    âĬĬ
    -0.18
    FOUNDATION
    -0.18
    taire
    -0.18
    POSITIVE LOGITS
    "url
    0.21
    |--
    0.21
    ewriter
    0.20
    å¶Ĥ
    0.20
    @student
    0.20
    oil
    0.19
    .optString
    0.19
    UserService
    0.19
    ournemouth
    0.19
    AffineTransform
    0.19
    Activations Density 0.001%

    No Known Activations