© 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. 879
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    åĭł
    -0.23
     definit
    -0.19
    å¾Ģå¤ĸ
    -0.19
    èĩªçĦ¶èĢĮ
    -0.18
    以人为
    -0.18
    izable
    -0.18
     UNUSED
    -0.18
    è¯ķè¯ķ
    -0.18
    åķ°
    -0.18
     shootout
    -0.17
    POSITIVE LOGITS
    ckt
    0.25
    ][/
    0.25
     Lumia
    0.23
    Éľ
    0.23
    byss
    0.22
    ombine
    0.22
    .UTC
    0.21
    bilder
    0.21
    تÙĦÙģزÙĬÙĪÙĨ
    0.20
    -Token
    0.20
    Activations Density 0.185%

    No Known Activations