© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3381
    Prev
    Next
    INDEX
    Explanations

    =

    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
    #aa
    -0.21
    UGIN
    -0.21
    ;base
    -0.21
    isans
    -0.21
     .'</
    -0.20
    #ab
    -0.20
    .']
    -0.20
    ç¿
    -0.19
     =>'
    -0.19
    #ga
    -0.19
    POSITIVE LOGITS
    ä»İ严
    0.20
     sublicense
    0.19
    opper
    0.19
    _thumbnail
    0.18
     dar
    0.18
    CAA
    0.18
    æµģéĢļ
    0.18
    åıªä¸įè¿ĩ
    0.18
     zab
    0.18
    usc
    0.18
    Activations Density 0.010%

    No Known Activations