© 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. 2691
    Prev
    Next
    INDEX
    Explanations

    materials

    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
    emetery
    -0.29
    ViewChild
    -0.23
    cuador
    -0.22
    SceneManager
    -0.21
    eturn
    -0.20
    [op
    -0.20
    :";č↵
    -0.20
     style
    -0.20
    ër
    -0.20
    ('../../../
    -0.20
    POSITIVE LOGITS
    åĪ¶åĵģ
    0.27
    åĪ¶æĪIJ
    0.26
    製
    0.26
    WARE
    0.22
     JpaRepository
    0.22
    æĿIJè´¨
    0.21
     pregn
    0.21
    obel
    0.20
     scram
    0.20
    wang
    0.20
    Activations Density 0.750%

    No Known Activations