© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 449
    Prev
    Next
    INDEX
    Explanations

    job titles

    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
    /GPL
    -0.24
    ëĵłì§Ģ
    -0.23
    bsites
    -0.23
    phans
    -0.22
    /stretch
    -0.22
    åĴĽ
    -0.22
     namoro
    -0.22
    arriv
    -0.21
     NDEBUG
    -0.21
    -scenes
    -0.21
    POSITIVE LOGITS
     who
    0.43
    们çļĦ
    0.40
    们
    0.36
    们éĥ½
    0.34
    è¿Ļ个èģĮä¸ļ
    0.33
    who
    0.32
    ship
    0.32
    æĺ¯è°ģ
    0.31
    åĢij
    0.29
    åħ¼
    0.28
    Activations Density 4.592%

    No Known Activations