© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2877
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    //{{
    -0.23
     either
    -0.22
    nesty
    -0.21
    -await
    -0.20
    对人ä½ĵ
    -0.20
    éĤ£äºĽ
    -0.19
    á»IJ
    -0.19
    家éķ¿ä»¬
    -0.19
    åIJįæ°Ķ
    -0.19
    æĪĸåħ¶ä»ĸ
    -0.19
    POSITIVE LOGITS
    第ä¸ī次
    0.21
    |array
    0.21
    ábado
    0.21
    .datatables
    0.20
     utan
    0.20
    instancetype
    0.20
    åįļæĸĩ
    0.20
    ç»
    0.20
     incidental
    0.20
    âĹĤ
    0.19
    Activations Density 0.701%

    No Known Activations