© 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
    2. Qwen2.5-7B-IT
    3. 20-MATRYOSHKA-65K
    4. 1358
    Prev
    Next
    INDEX
    Explanations

    documentary film

    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
     “
    -0.32
    ↵↵
    -0.31
    ...↵↵
    -0.30
     
    -0.29
     "
    -0.28
    ...↵
    -0.28
    ↵↵↵
    -0.28
    :↵↵
    -0.25
    -"
    -0.25
    ↵
    -0.25
    POSITIVE LOGITS
    PCS
    0.31
    '>".$
    0.30
    BOSE
    0.29
    GPC
    0.29
    âĢ¥
    0.28
     "','
    0.26
    â̦â̦
    0.25
    EFR
    0.25
     millenn
    0.25
    ðŁĵIJ
    0.25
    Activations Density 1.347%

    No Known Activations