© 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. 2268
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    --------------------------------------------------------------------------↵
    -0.22
    绶
    -0.22
    elocity
    -0.21
    æŁ¥çľĭåħ¨æĸĩ
    -0.21
    ä¸įåı¯æĪĸ
    -0.21
    semi
    -0.21
     NUIT
    -0.20
    PIP
    -0.20
    __':č↵
    -0.20
    escription
    -0.20
    POSITIVE LOGITS
    2
    0.23
    1
    0.21
    OldData
    0.21
    clare
    0.21
    éĩĩæļĸ
    0.20
    9
    0.20
    iance
    0.20
    3
    0.20
     emph
    0.20
     redistrib
    0.19
    Activations Density 0.001%

    No Known Activations