© 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
    2. Qwen2.5-7B-IT
    3. 20-MATRYOSHKA-65K
    4. 595
    Prev
    Next
    INDEX
    Explanations

    capabilit(y/ies)

    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
    readcr
    -0.28
     zwarte
    -0.25
    oader
    -0.25
     dikke
    -0.24
    Sharper
    -0.24
    ibox
    -0.23
    Assignable
    -0.23
    “
    -0.22
    подоб
    -0.22
    ennifer
    -0.21
    POSITIVE LOGITS
    ÑĤвеÑĢжда
    0.29
    able
    0.29
    ÑĤвеÑĢжден
    0.28
    ables
    0.26
    ings
    0.26
    ers
    0.26
    ordova
    0.26
    :".$
    0.25
    轫
    0.25
    女æĢ§æľĭåıĭ
    0.24
    Activations Density 12.441%

    No Known Activations