© 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. 428
    Prev
    Next
    INDEX
    Explanations

    numbers or patents

    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
    peater
    -0.28
    éĵ©
    -0.25
    æĩij
    -0.24
    anganese
    -0.23
    ombine
    -0.23
    åĪĨ彩
    -0.23
     htmlentities
    -0.23
    oggler
    -0.23
    èĵł
    -0.21
    apg
    -0.21
    POSITIVE LOGITS
     TMPro
    0.27
    ÑģÑĤÑĢаива
    0.27
     bureaucr
    0.26
     ACPI
    0.25
     (~(
    0.23
    odore
    0.23
     controlId
    0.23
     bey
    0.22
    !!");↵
    0.21
     intimid
    0.21
    Activations Density 2.100%

    No Known Activations