© 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. 675
    Prev
    Next
    INDEX
    Explanations

    code symbols

    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
    -0.28
     Nutzung
    -0.27
     Según
    -0.23
     Más
    -0.22
    itez
    -0.21
     Unterstützung
    -0.20
    åĩºç§Ł
    -0.20
    dued
    -0.20
     commenter
    -0.20
    âce
    -0.20
    POSITIVE LOGITS
     (){
    0.32
    âķ¯
    0.29
     çĶŁåij½åij¨æľŁ
    0.28
     }},↵
    0.28
    :".$
    0.28
    å¾Īå¤ļçݩ家
    0.28
    âĹĢ
    0.27
    :'.$
    0.25
    :animated
    0.25
    ->{_
    0.25
    Activations Density 0.394%

    No Known Activations