© 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. 2790
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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
     ''){↵
    -0.19
     Spirits
    -0.19
    ãĥ«ãĥ¼
    -0.19
    nels
    -0.18
     fierc
    -0.18
    IFIC
    -0.18
    ï¼ģï¼ģ↵↵
    -0.18
    æ£ķ
    -0.18
     Downs
    -0.18
    aramel
    -0.18
    POSITIVE LOGITS
    ivia
    0.20
    CBC
    0.20
    thouse
    0.20
     Kaplan
    0.19
    ."',
    0.19
    >Nama
    0.19
     true
    0.18
    ÐŁÐ¾Ð´ÑĢобнее
    0.18
    .calc
    0.18
    ç¥ĸçĪ¶
    0.18
    Activations Density 0.161%

    No Known Activations