© 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. 29
    Prev
    Next
    INDEX
    Explanations

    name

    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
    textarea
    -0.20
    hetto
    -0.20
    ({});↵
    -0.20
    ospel
    -0.20
     definition
    -0.19
    æĢģ
    -0.19
    被è§Ĩ为
    -0.19
    dì
    -0.18
    <textarea
    -0.18
    çĮĸ
    -0.18
    POSITIVE LOGITS
     name
    0.55
    åIJį称
    0.54
    åIJįåŃĹ
    0.51
     names
    0.50
    name
    0.48
    çļĦåIJįåŃĹ
    0.47
    -name
    0.44
    .name
    0.42
    è¿Ļ个åIJįåŃĹ
    0.41
    _name
    0.40
    Activations Density 3.383%

    No Known Activations