© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1580
    Prev
    Next
    INDEX
    Explanations

    you or your

    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
    /↵↵↵↵
    -0.43
    :".$
    -0.42
    #ga
    -0.39
    __;
    -0.37
    ,www
    -0.36
    ,Th
    -0.35
    :'.$
    -0.34
     ());↵↵
    -0.34
    -UA
    -0.33
    .AI
    -0.33
    POSITIVE LOGITS
     your
    0.43
    your
    0.39
     you
    0.38
    Your
    0.36
    ä½łçļĦ
    0.35
     Your
    0.34
     You
    0.31
    ä½łèĩªå·±
    0.31
     yourself
    0.30
     yours
    0.30
    Activations Density 2.586%

    No Known Activations