© 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. 2385
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

    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
    åĨľåī¯äº§åĵģ
    -0.20
    .setY
    -0.19
    太ä¹ħ
    -0.19
    浩
    -0.18
     perms
    -0.18
     BAB
    -0.18
     boast
    -0.18
     bottoms
    -0.18
    论è¯ģ
    -0.18
     ׾×Ĵ
    -0.18
    POSITIVE LOGITS
    ='<?
    0.25
    åĹIJ
    0.24
     {{--<
    0.24
    ceipt
    0.23
    ustum
    0.23
    hế
    0.22
    OffsetTable
    0.22
     {?>↵
    0.22
    ernals
    0.22
    ÑģÑĤÑĮÑİ
    0.21
    Activations Density 0.001%

    No Known Activations