© 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. 800
    Prev
    Next
    INDEX
    Explanations

    technical and news

    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
     CONTR
    -0.21
     ÑģмÑĭÑģл
    -0.20
     Moj
    -0.19
    çľŃ
    -0.19
     shouts
    -0.19
    åĽ½å®¶éĩįçĤ¹
    -0.18
     Vinyl
    -0.18
    postalcode
    -0.18
    reibung
    -0.18
    brid
    -0.18
    POSITIVE LOGITS
    >tag
    0.27
    traîn
    0.25
    OfString
    0.23
    (@"%@",
    0.23
    åĺģ
    0.23
    uxtap
    0.22
    .AF
    0.22
    .SizeType
    0.22
    -describedby
    0.21
    éĥ¨åī¯
    0.21
    Activations Density 0.068%

    No Known Activations