© 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. 2197
    Prev
    Next
    INDEX
    Explanations

    code and technical

    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
    çīĪæĿĥå½Ĵ
    -0.25
    IGIN
    -0.23
    游æĪıæĬĢå·§
    -0.21
     Tradable
    -0.20
     oppos
    -0.20
     bureaucr
    -0.19
    usalem
    -0.18
     destinationViewController
    -0.18
    åįĬ导
    -0.18
     madrid
    -0.18
    POSITIVE LOGITS
    __);↵↵
    0.22
    )(((
    0.20
    ExceptionHandler
    0.20
    çŨ
    0.20
    _SU
    0.19
    :CGRect
    0.19
     Ness
    0.19
     Bil
    0.19
    jen
    0.18
    %";↵
    0.18
    Activations Density 0.001%

    No Known Activations