© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4214
    Prev
    Next
    INDEX
    Explanations

    technical code

    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
    Negative Logits
    .assertNull
    -0.23
    otre
    -0.21
    apolis
    -0.21
     Erectile
    -0.21
     ámb
    -0.20
     Ebook
    -0.20
     defensively
    -0.19
     Verb
    -0.19
    LayoutManager
    -0.19
    )dealloc
    -0.19
    POSITIVE LOGITS
     }?>↵
    0.22
    @endforeach
    0.21
    è¿ijè·Ŀ离
    0.21
     MEDIATEK
    0.19
    indhoven
    0.19
    èĭĮ
    0.18
     meille
    0.17
    peater
    0.17
    ç©´ä½į
    0.17
    -eslint
    0.17
    Activations Density 0.008%

    No Known Activations