© 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. 586
    Prev
    Next
    INDEX
    Explanations

    construction components

    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
    /ay
    -0.39
    /Branch
    -0.38
    /lg
    -0.37
    ?option
    -0.37
    /goto
    -0.37
    /Gate
    -0.37
    /↵↵↵↵
    -0.36
    /tos
    -0.36
    /gpio
    -0.34
    />.
    -0.34
    POSITIVE LOGITS
     Kardash
    0.33
     démarch
    0.28
    æĹ¶ä»£ä¸ŃåĽ½
    0.28
     fierc
    0.27
    ç½ijé¦ĸ页
    0.27
    游æĪıå½ĵä¸Ń
    0.26
    娱ä¹IJåľº
    0.25
     fiance
    0.25
     domina
    0.25
    娱ä¹IJå¹³åı°
    0.24
    Activations Density 80.497%

    No Known Activations