© 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. 254
    Prev
    Next
    INDEX
    Explanations

    code and symbols

    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
     desar
    -0.26
    ::
    -0.22
    _detalle
    -0.21
    åİ¿éķ¿
    -0.21
    atonin
    -0.20
    NamedQuery
    -0.20
     smarty
    -0.19
    fe
    -0.19
     heightFor
    -0.19
    çıŃéķ¿
    -0.19
    POSITIVE LOGITS
    .labelX
    0.26
    ä½ıæĪ¿åħ¬ç§¯
    0.26
    :maj
    0.25
    åıĸåĨ³
    0.25
    ].'
    0.25
    [Index
    0.24
    ksam
    0.24
    ={({
    0.24
    "profile
    0.24
    ç½ijç«Ļåľ°åĽ¾
    0.23
    Activations Density 1.750%

    No Known Activations