© 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. 1028
    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
    åij²
    -0.22
    é¾ĩ
    -0.20
     being
    -0.20
    BASEPATH
    -0.20
    注æĺİåĩºå¤Ħ
    -0.19
    à¸Ńำà¹Ģà¸ł
    -0.19
    é¦Ĺ
    -0.19
     пÑĢодÑĥкÑĨии
    -0.19
    èħĺ
    -0.19
    èĥ±
    -0.19
    POSITIVE LOGITS
    /Dk
    0.26
    )||(
    0.25
     Conte
    0.25
    adoo
    0.23
    tings
    0.23
    ,Th
    0.23
    engers
    0.22
     Ãĸn
    0.22
    aroo
    0.22
    -league
    0.22
    Activations Density 0.137%

    No Known Activations