© 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. 1520
    Prev
    Next
    INDEX
    Explanations

    Q/A format

    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
    DATED
    -0.21
    åīįè¡Į
    -0.19
    è¯Ŀ
    -0.19
    ÄĻp
    -0.19
    poons
    -0.18
     componentDid
    -0.18
     masturb
    -0.18
    å¤ļç§įå½¢å¼ı
    -0.18
    æľī幸
    -0.18
    ä¼ī
    -0.18
    POSITIVE LOGITS
    /pm
    0.25
    Vien
    0.24
    .newLine
    0.20
    onto
    0.19
    stdarg
    0.19
    licer
    0.19
    aled
    0.19
    ="{!!
    0.19
    qus
    0.19
    以为
    0.19
    Activations Density 0.001%

    No Known Activations