© 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. 1686
    Prev
    Next
    INDEX
    Explanations

    I

    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
    .RestController
    -0.25
     untranslated
    -0.22
    اØŃتÙħ
    -0.22
    AdminController
    -0.21
    SetActive
    -0.21
    ewire
    -0.21
    chestra
    -0.21
    azı
    -0.21
     onDataChange
    -0.21
    ISTORY
    -0.20
    POSITIVE LOGITS
    ’ve
    0.28
    've
    0.28
    /she
    0.27
    ’d
    0.25
    ’ll
    0.25
     beÄŁen
    0.25
    'll
    0.25
    'd
    0.24
     can
    0.23
    âĤ½
    0.23
    Activations Density 2.487%

    No Known Activations