© 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. 1535
    Prev
    Next
    INDEX
    Explanations

    list items

    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
    æ©IJ
    -0.21
    åĦ¿
    -0.21
     hairst
    -0.21
    toUpperCase
    -0.20
    çĸ¡
    -0.19
    æ²Ĩ
    -0.19
    ç³Ĺ
    -0.18
    _VOL
    -0.18
    -0.18
    .writeString
    -0.18
    POSITIVE LOGITS
    ".↵↵↵↵
    0.30
     disappe
    0.29
     ×Ķ×ķ×ĵ
    0.26
    âĦħ
    0.26
    /GPL
    0.26
    åħ¨èµĦåŃIJ
    0.25
    :System
    0.25
    -UA
    0.25
    :animated
    0.24
    :<?
    0.24
    Activations Density 0.230%

    No Known Activations