© 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. 1338
    Prev
    Next
    INDEX
    Explanations

    corrupted text

    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
    hores
    -0.33
     emailAddress
    -0.27
     Ñģдела
    -0.26
     acompaña
    -0.26
    endsWith
    -0.25
     subrange
    -0.25
     (!((
    -0.24
     userEmail
    -0.24
    %X
    -0.23
    atables
    -0.23
    POSITIVE LOGITS
    éħĬ
    0.27
     cosplay
    0.26
     FUCK
    0.26
     newPosition
    0.26
     IonicPage
    0.26
    éĩİå¤ĸ
    0.25
    主è¦ģéĽĨä¸Ń
    0.25
    /↵↵↵↵
    0.24
     nutrient
    0.24
     raping
    0.24
    Activations Density 4.151%

    No Known Activations