© 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. 1048
    Prev
    Next
    INDEX
    Explanations

    =

    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
    çŀĮ
    -0.23
    umpt
    -0.21
    åħħ
    -0.20
     ApiService
    -0.19
     AuthenticationService
    -0.19
    åĴİ
    -0.19
     didSelectRowAtIndexPath
    -0.18
     HeaderComponent
    -0.18
     sovere
    -0.18
    Actualizar
    -0.18
    POSITIVE LOGITS
    âĦī
    0.28
    esteem
    0.26
    =?";↵
    0.24
    ToBounds
    0.22
    });↵↵↵↵
    0.21
    .Networking
    0.21
    --+
    0.20
    ,GL
    0.20
    iá»ĩu
    0.20
     (){
    0.19
    Activations Density 0.025%

    No Known Activations