© 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. 1564
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    IFn
    -0.41
    -Semit
    -0.36
    berra
    -0.33
    /Dk
    -0.32
    .AutoComplete
    -0.32
    /Internal
    -0.32
    iquement
    -0.31
    étude
    -0.30
    /Instruction
    -0.30
     undermin
    -0.29
    POSITIVE LOGITS
     appré
    0.35
     difficulté
    0.28
     signings
    0.28
    èī¾æ»ĭ
    0.27
     appréci
    0.25
     intimid
    0.24
    ç³ĸå°¿
    0.24
     Führung
    0.23
     décid
    0.23
     snapchat
    0.23
    Activations Density 10.111%

    No Known Activations