© 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. 684
    Prev
    Next
    INDEX
    Explanations

    periods

    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
     (*((
    -0.30
     Phonetic
    -0.30
     AppleWebKit
    -0.28
     burge
    -0.27
     cuz
    -0.27
    èĴIJéĽĨ
    -0.26
    -Owned
    -0.26
     FAG
    -0.26
     Gratuit
    -0.25
    -initialized
    -0.23
    POSITIVE LOGITS
    ={"/
    0.26
     ëĭ¤ë§Į
    0.25
    èĤĦ
    0.24
    .yy
    0.23
     It
    0.23
    娱ä¹IJå¹³åı°
    0.23
    ennifer
    0.23
     There
    0.23
     ><?
    0.22
    pollo
    0.22
    Activations Density 2.308%

    No Known Activations