© 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. 975
    Prev
    Next
    INDEX
    Explanations

    document metadata

    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
    ðŁĵIJ
    -0.34
    âļĹ
    -0.33
     fkk
    -0.26
    âĺ°
    -0.26
    /INFO
    -0.25
    /MPL
    -0.25
    æ·ı
    -0.24
    âĮĤ
    -0.24
    iosk
    -0.23
    ’B
    -0.23
    POSITIVE LOGITS
    女æĢ§æľĭåıĭ
    0.20
     apologise
    0.20
     migliori
    0.20
    çļĦç¼ĺ
    0.19
    åıĸåĨ³
    0.19
     hall
    0.18
    endsWith
    0.18
     provided
    0.18
    nd
    0.18
     withStyles
    0.18
    Activations Density 0.011%

    No Known Activations