© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 153
    Prev
    Next
    INDEX
    Explanations

    citations

    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
    ((__
    -0.25
    >>↵↵
    -0.21
     Ä°l
    -0.20
    ORA
    -0.20
    omez
    -0.19
     Hã
    -0.19
    Textarea
    -0.19
    uhn
    -0.19
    uyo
    -0.19
    FromClass
    -0.19
    POSITIVE LOGITS
    aeda
    0.24
    /inet
    0.23
     ,
    0.22
     ,č↵
    0.22
    建档ç«ĭ
    0.22
    traî
    0.21
    outu
    0.21
     enthus
    0.21
    agnar
    0.20
    çºłéĶĻ
    0.20
    Activations Density 0.227%

    No Known Activations