© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3987
    Prev
    Next
    INDEX
    Explanations

    B

    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
    æĤ»
    -0.32
    对çħ§æ£ĢæŁ¥
    -0.26
    å¤įå·¥å¤į
    -0.23
    ayload
    -0.22
     karakter
    -0.22
    个交æĺĵ
    -0.22
    åıĪ好åıĪå¿«
    -0.22
     COUNTY
    -0.21
    									↵
    -0.20
     oma
    -0.20
    POSITIVE LOGITS
    uforia
    0.28
    izador
    0.28
    bsite
    0.27
    isers
    0.26
    ackbar
    0.25
    acists
    0.25
    gger
    0.24
    awei
    0.24
    acı
    0.23
    ropri
    0.23
    Activations Density 0.013%

    No Known Activations