© 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. 1925
    Prev
    Next
    INDEX
    Explanations

    word parts

    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
    gether
    -0.34
    onical
    -0.29
    theless
    -0.26
    oriously
    -0.25
    otros
    -0.24
    @dynamic
    -0.24
    akest
    -0.23
    plier
    -0.23
    tempt
    -0.23
    onacci
    -0.23
    POSITIVE LOGITS
    åĵĪåĵĪåĵĪåĵĪ
    0.25
    -Owned
    0.22
    []{↵
    0.21
    è®°èĢħäºĨ解
    0.20
    åĬ¨çĶŁæĪIJ
    0.20
    çĿĢä»ĸ
    0.20
    'options
    0.19
    åĵĪåĵĪåĵĪ
    0.19
    åij¸
    0.19
    ฤษ
    0.19
    Activations Density 4.581%

    No Known Activations