© 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. 1170
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     Publié
    -0.25
     Rencontre
    -0.24
    çŀł
    -0.22
     Nightmare
    -0.22
    èīı
    -0.21
     maduras
    -0.21
     Bite
    -0.21
     Stamina
    -0.21
     consc
    -0.20
    oriously
    -0.20
    POSITIVE LOGITS
     Inc
    0.33
    Inc
    0.26
     Jr
    0.26
    "path
    0.23
    ingleton
    0.22
     Ltd
    0.22
     inc
    0.22
     "'";↵
    0.21
    inc
    0.20
    INC
    0.20
    Activations Density 1.141%

    No Known Activations