© 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. 233
    Prev
    Next
    INDEX
    Explanations

    code and numbers

    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
    AMY
    -0.30
     Ấ
    -0.25
     **)&
    -0.24
    -translate
    -0.23
    .epam
    -0.22
    "url
    -0.22
    .rar
    -0.22
     èĩªåĬ¨çĶŁæĪIJ
    -0.21
     tatto
    -0.20
    âĩĵ
    -0.20
    POSITIVE LOGITS
     Decompiled
    0.23
     mask
    0.21
     bit
    0.20
     bits
    0.20
    ifter
    0.20
    mask
    0.19
    elfast
    0.19
    мел
    0.19
    æİ©
    0.19
    onnen
    0.19
    Activations Density 0.207%

    No Known Activations