© 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. 946
    Prev
    Next
    INDEX
    Explanations

    full complete

    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
    esteem
    -0.26
    macen
    -0.26
     AndAlso
    -0.24
     èĭ¥è¦ģ
    -0.24
    swick
    -0.24
     }?>↵
    -0.23
    möglich
    -0.23
    delivr
    -0.22
     AssemblyVersion
    -0.21
    âĨĺ
    -0.21
    POSITIVE LOGITS
    /full
    0.45
    å®Įæķ´çļĦ
    0.41
    å®Įæķ´
    0.38
     full
    0.37
     complete
    0.36
    (full
    0.33
     fully
    0.31
    -full
    0.31
    åħ¨
    0.31
    ledged
    0.29
    Activations Density 1.327%

    No Known Activations