© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23234
    Prev
    Next
    INDEX
    Explanations

    IDs and numbers

    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
    æĹ¥æĿ¥
    -0.07
    ÙĬÙĨØ©
    -0.07
    客
    -0.07
    ubin
    -0.07
    _equals
    -0.07
    tta
    -0.07
     Jat
    -0.07
    æĭĤ
    -0.07
    çļĦåħīèĬĴ
    -0.07
    cht
    -0.07
    POSITIVE LOGITS
    TestId
    0.08
    åı·çłģ
    0.07
     numbers
    0.07
     seventy
    0.07
     ë²Īíĺ¸
    0.07
     номеÑĢ
    0.07
    NUMBER
    0.07
    IDS
    0.06
    resso
    0.06
    çķªåı·
    0.06
    Activations Density 0.142%

    No Known Activations