© 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. 2351
    Prev
    Next
    INDEX
    Explanations

    non-English characters

    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
    vertiser
    -0.24
    ksam
    -0.24
    -'.$
    -0.23
    ç¡ķ士çłĶ究
    -0.22
    .SwingConstants
    -0.21
    家éĥ½çŁ¥éģĵ
    -0.21
    (connectionString
    -0.21
    "],["
    -0.21
    loses
    -0.21
    loggedIn
    -0.20
    POSITIVE LOGITS
    顾
    0.19
    (PORT
    0.19
    å¯Ĩ
    0.18
    ëŀ¬
    0.17
    ilian
    0.17
    ели
    0.17
    çľģ
    0.17
     propName
    0.17
    ç¬Ħ
    0.17
    _EOF
    0.17
    Activations Density 0.001%

    No Known Activations