© 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. 2495
    Prev
    Next
    INDEX
    Explanations

    research findings

    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
    DialogContent
    -0.23
    ='<?
    -0.23
    ERVED
    -0.22
     sample
    -0.21
    ÑĩÑĥвÑģÑĤв
    -0.20
    éĩĩçŁ¿çŃī
    -0.20
     Kraft
    -0.20
     Rentals
    -0.19
    éĶ¨
    -0.19
     sockfd
    -0.18
    POSITIVE LOGITS
    CCCCCC
    0.23
    /+
    0.21
     Circuit
    0.21
    geois
    0.20
    FormatException
    0.20
    azo
    0.20
    vos
    0.20
     discovery
    0.19
    Ÿ
    0.19
    UGIN
    0.19
    Activations Density 0.582%

    No Known Activations