© 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. 66
    Prev
    Next
    INDEX
    Explanations

    code libraries

    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
     )↵↵↵↵↵↵↵↵
    -0.30
    对åħ¶çľŁå®ŀ
    -0.30
    estruction
    -0.28
     tats
    -0.27
    ECTOR
    -0.27
    女æĢ§æľĭåıĭ
    -0.27
    âļĹ
    -0.27
     nors
    -0.27
    Sharper
    -0.26
    ðŁĵIJ
    -0.26
    POSITIVE LOGITS
    'icon
    0.31
    riott
    0.27
    .fasterxml
    0.26
    akedown
    0.25
    éducation
    0.24
    ÑĤвеÑĢжда
    0.23
    apesh
    0.23
    ستÙħرار
    0.22
    è¥ģ
    0.22
    reeze
    0.22
    Activations Density 6.981%

    No Known Activations