© 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. 3058
    Prev
    Next
    INDEX
    Explanations

    specific entities

    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
    åĽ½æ°ijç»ıæµİ
    -0.22
    èľķ
    -0.20
    ch
    -0.20
    ponce
    -0.20
    æł¹æľ¬å°±ä¸į
    -0.20
     Ta
    -0.20
    å®ŀå¹²
    -0.20
     Liz
    -0.19
     searchData
    -0.18
    åľ¨çİ°åľº
    -0.18
    POSITIVE LOGITS
    leanor
    0.30
    ereotype
    0.29
    []{↵
    0.27
    agraph
    0.25
    imei
    0.24
    orate
    0.24
    ilon
    0.24
    lijah
    0.24
    asons
    0.23
    omite
    0.23
    Activations Density 0.001%

    No Known Activations