© 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. 791
    Prev
    Next
    INDEX
    Explanations

    foreign or unusual characters

    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
     misunder
    -0.40
    /legal
    -0.40
     relent
    -0.40
    /lic
    -0.38
     unfavor
    -0.35
    ".↵↵↵↵
    -0.34
    /stretch
    -0.32
    /mit
    -0.32
    /GPL
    -0.32
     cuckold
    -0.32
    POSITIVE LOGITS
    娱ä¹IJåľº
    0.41
     démarch
    0.38
    女æĢ§æľĭåıĭ
    0.36
     enthus
    0.35
     lingerie
    0.34
    à¸Ľà¸£à¸°à¹Ģม
    0.34
    æݨä»ĭä¼ļ
    0.32
    娱ä¹IJå¹³åı°
    0.32
     INCLUDED
    0.31
     saddened
    0.30
    Activations Density 30.486%

    No Known Activations