© 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. 2939
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    nosis
    -0.21
    ç¿°
    -0.20
     konk
    -0.20
    ishops
    -0.19
    [prop
    -0.19
    .RestController
    -0.19
    indh
    -0.19
     &
    -0.19
    åĵĤ
    -0.19
     slik
    -0.19
    POSITIVE LOGITS
    æĹłè®ºæĺ¯åħ¶
    0.27
    æľīçļĦçݩ家
    0.26
    åľ¨ä¼łå¥ĩ
    0.23
    çݩ家æľĭåıĭ
    0.23
     )↵↵↵↵↵↵↵↵
    0.22
    GenerationStrategy
    0.22
    ?"↵↵↵↵
    0.21
    datable
    0.21
    reactstrap
    0.21
     Dabei
    0.20
    Activations Density 0.031%

    No Known Activations