© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 3184
    Prev
    Next
    INDEX
    Explanations

    berries and fruits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æºIJåľ°
    -0.07
     пÑĢобе
    -0.07
    çī¹éĴ¢
    -0.07
    æµģåĬ¨
    -0.07
    holm
    -0.07
     полоÑģ
    -0.07
    漪
    -0.07
     brid
    -0.07
    _PC
    -0.07
    brid
    -0.07
    POSITIVE LOGITS
    å½¢å¼ı
    0.07
    اذ
    0.07
    æĺĵçĪĨ
    0.07
    顶端
    0.07
     rapat
    0.07
    åıijèĤ²
    0.07
    çļĦå½¢å¼ı
    0.07
    åijĪ
    0.07
    表çİ°å½¢å¼ı
    0.07
    åįģæĹ¥
    0.07
    Activations Density 0.025%

    No Known Activations