© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3102
    Prev
    Next
    INDEX
    Explanations

    code fragments

    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
     @$_
    -0.24
     kaps
    -0.21
     scarc
    -0.21
     htons
    -0.20
     rekl
    -0.20
     má»ıi
    -0.19
     htonl
    -0.19
    åŃ¦ä¹łæĪIJ绩
    -0.19
    ificados
    -0.19
    èĽ±
    -0.19
    POSITIVE LOGITS
     ".";↵
    0.23
     fkk
    0.23
    irs
    0.20
    éĤĭ
    0.20
    åĭį
    0.20
    å´´
    0.20
    溦
    0.19
    odos
    0.19
    elves
    0.19
    /↵↵↵↵
    0.19
    Activations Density 0.006%

    No Known Activations