© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2836
    Prev
    Next
    INDEX
    Explanations

    food and drink

    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
    ');↵↵↵↵
    -0.25
    mát
    -0.25
    IJľ
    -0.25
     AndAlso
    -0.24
    إرÙĩاب
    -0.23
    WISE
    -0.23
     getpid
    -0.23
     }}"><
    -0.22
    íĶ½
    -0.22
    -Semit
    -0.22
    POSITIVE LOGITS
    /slick
    0.23
    è¾ħ
    0.23
    æ±Ĩ
    0.21
    <stdlib
    0.20
    å·§
    0.19
     awakeFromNib
    0.19
     alternating
    0.19
    ÑĪки
    0.19
     Arm
    0.18
    ooky
    0.18
    Activations Density 0.001%

    No Known Activations