© 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. 12476
    Prev
    Next
    INDEX
    Explanations

    cave painting, eighteen amendment, drive, engine, shoes, nucleus

    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
     far
    -0.07
    zos
    -0.07
    arc
    -0.06
    以便äºİ
    -0.06
     Tiong
    -0.06
    æĽ´æľīåĪ©äºİ
    -0.06
    leh
    -0.06
    yon
    -0.06
    Far
    -0.06
    exion
    -0.06
    POSITIVE LOGITS
    æīĢ为
    0.10
    ault
    0.07
    为代表
    0.07
    èĮ¨
    0.07
    客çļĦ
    0.07
    _alloc
    0.07
    anean
    0.07
    îtr
    0.07
    uja
    0.07
    eways
    0.07
    Activations Density 0.030%

    No Known Activations