© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1146
    Prev
    Next
    INDEX
    Explanations

    say numbers

    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
    åįĹæµ·ç½ij
    -0.23
    	Copyright
    -0.22
    ábado
    -0.22
    è¯Į
    -0.20
     sequelize
    -0.20
     iar
    -0.20
    è´´åIJ§
    -0.20
    çļĦæĥħ绪
    -0.19
    åħ¶å®ĥéĹ®é¢ĺ
    -0.19
    |--------------------------------------------------------------------------↵
    -0.19
    POSITIVE LOGITS
     libertine
    0.32
     Kardash
    0.28
    kest
    0.24
     burge
    0.24
     misogyn
    0.23
    <decltype
    0.23
     potrÃł
    0.23
    *size
    0.23
     appré
    0.23
     Clintons
    0.23
    Activations Density 0.245%

    No Known Activations