© 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. 1427
    Prev
    Next
    INDEX
    Explanations

    code or math

    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
    éªľ
    -0.23
    ÃŃculo
    -0.23
     cocci
    -0.23
     Goblin
    -0.22
     Polyester
    -0.22
    ;"><?
    -0.22
    è§IJ
    -0.22
    babel
    -0.21
    åıĪ好åıĪå¿«
    -0.21
    ä¸ĥåįģ
    -0.20
    POSITIVE LOGITS
    :".$
    0.30
    /Branch
    0.30
    _marshall
    0.28
    /Instruction
    0.28
    /↵↵↵↵
    0.28
     (;;
    0.27
    /,↵
    0.26
    linky
    0.25
    AdapterManager
    0.25
    });↵↵↵↵
    0.24
    Activations Density 0.442%

    No Known Activations