© 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. 1160
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
     (?
    -0.27
     (?)
    -0.26
     ])->
    -0.24
    (?
    -0.22
     probably
    -0.22
    ynamo
    -0.22
     Very
    -0.21
    ildenafil
    -0.21
    abbix
    -0.21
     However
    -0.21
    POSITIVE LOGITS
    ï¼Ł↵
    0.54
    ï¼Ł↵↵
    0.48
    ØŁ
    0.47
    ?↵
    0.46
    ï¼Ł
    0.45
    ï¼Ł”
    0.42
    ?↵↵
    0.41
    ?"↵
    0.40
    ?\
    0.39
    ï¼ŁãĢį
    0.39
    Activations Density 3.410%

    No Known Activations