© 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. 1021
    Prev
    Next
    INDEX
    Explanations

    structure morphology

    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
    #ab
    -0.31
    #ac
    -0.27
    åŀŁ
    -0.25
    ournaments
    -0.24
    #aa
    -0.24
    traî
    -0.24
    lève
    -0.23
     lesb
    -0.22
    ogenerated
    -0.22
    earable
    -0.22
    POSITIVE LOGITS
    åıĺè¿ģ
    0.30
    åĴĮåıijå±ķ
    0.29
    çī¹çĤ¹
    0.28
    åıĺåĮĸ
    0.25
    /style
    0.24
    åIJĦå¼Ĥ
    0.24
     change
    0.24
    çļĦåıĺåĮĸ
    0.24
    åĴĮæĬĢæľ¯
    0.23
    çī¹å¾ģ
    0.22
    Activations Density 6.834%

    No Known Activations