© 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. 8976
    Prev
    Next
    INDEX
    Explanations

    threat detectors

    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
     آش
    -0.07
    rodom
    -0.07
    onus
    -0.07
    ilet
    -0.07
    翼翼
    -0.07
    reste
    -0.07
    åIJijä¸Ĭ级
    -0.06
    indo
    -0.06
    uhkan
    -0.06
    奸
    -0.06
    POSITIVE LOGITS
    åĩºå¥ĩ
    0.08
    моÑĤ
    0.07
    mati
    0.07
    _FACT
    0.07
    æĴµ
    0.07
    èĢĥæĭī
    0.07
    بع
    0.07
    ÙħÙĪÙĦ
    0.07
    大湾åĮº
    0.06
    æ·±åħ¥çłĶ究
    0.06
    Activations Density 0.006%

    No Known Activations