© 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. 932
    Prev
    Next
    INDEX
    Explanations

    technical communications

    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
    åķ»
    -0.27
    Ø£ÙĪض
    -0.25
    odynam
    -0.24
     dicks
    -0.23
     acomp
    -0.23
    إصÙĦاØŃ
    -0.23
     indeb
    -0.23
     resil
    -0.22
    izador
    -0.22
    إعÙĦاÙĨ
    -0.22
    POSITIVE LOGITS
    ness
    0.34
    تظاÙĩر
    0.29
    إز
    0.28
    تغÙĬ
    0.26
    ependency
    0.26
    أربع
    0.25
    Ø£Ùģر
    0.25
    استÙĤÙĦ
    0.24
    hoot
    0.24
    NESS
    0.24
    Activations Density 3.890%

    No Known Activations