© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 970
    Prev
    Next
    INDEX
    Explanations

    say "."

    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
    .fromFunction
    -0.33
    .visitMethod
    -0.25
    etroit
    -0.24
    éħ½
    -0.23
    styleType
    -0.22
    ornment
    -0.22
    Haunted
    -0.21
    .SizeType
    -0.21
    .faceVertexUvs
    -0.21
    fillType
    -0.21
    POSITIVE LOGITS
    åıĪ好åıĪå¿«
    0.27
    é«Į
    0.26
    .get
    0.23
    lef
    0.23
    slick
    0.22
    æīĢ
    0.21
     Erectile
    0.20
    æīĢåľ¨çļĦ
    0.20
    çļĦ
    0.20
    ÅĤoż
    0.20
    Activations Density 0.758%

    No Known Activations