© 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. 679
    Prev
    Next
    INDEX
    Explanations

    math and code

    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
     untranslated
    -0.28
     GANG
    -0.24
    ç½ijåºĹ
    -0.24
     filmer
    -0.24
    è¦ģéĹ»
    -0.23
     pregn
    -0.23
    éĶ¦æłĩ
    -0.22
     Gratuit
    -0.21
    æ¨Ĺ
    -0.21
    paralleled
    -0.21
    POSITIVE LOGITS
    @Web
    0.29
    讵
    0.25
    Mathf
    0.22
    ModifiedDate
    0.22
    .nickname
    0.21
     modalitÃł
    0.21
    keterangan
    0.21
    .epam
    0.20
    *)"
    0.20
    ä¹łè¿ijå¹³æĸ°
    0.20
    Activations Density 0.464%

    No Known Activations