© 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. 160
    Prev
    Next
    INDEX
    Explanations

    exposure

    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
    éĶį
    -0.24
     automát
    -0.23
    çĤ·
    -0.21
     AsyncStorage
    -0.21
    .deleteById
    -0.21
    achable
    -0.21
     ()=>{↵
    -0.21
     },{
    -0.20
    ()=>
    -0.19
    -automatic
    -0.19
    POSITIVE LOGITS
     exposure
    0.27
    æĿ¡ä»¶
    0.26
     воздейÑģÑĤв
    0.25
     alone
    0.25
     conditions
    0.24
     exposures
    0.24
    æĿ¡ä»¶ä¸ĭ
    0.24
     experimental
    0.23
     environments
    0.23
     imposed
    0.23
    Activations Density 3.869%

    No Known Activations