© 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. 1225
    Prev
    Next
    INDEX
    Explanations

    say "("

    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
    (Throwable
    -0.23
    èµ°åĬ¿åĽ¾
    -0.22
    (""),
    -0.20
    ized
    -0.19
    ly
    -0.19
    æĿ¡è¯Ħ论
    -0.19
    è®°èĢħäºĨ解
    -0.19
    UITableViewCell
    -0.18
    <fieldset
    -0.18
     '::
    -0.18
    POSITIVE LOGITS
    (č↵
    0.31
    (↵
    0.28
     nigeria
    0.27
     philippines
    0.26
    :animated
    0.26
     (č↵
    0.25
    :'.$
    0.25
    leftright
    0.25
    MMdd
    0.25
    )↵↵↵↵↵↵↵↵
    0.25
    Activations Density 0.892%

    No Known Activations