© 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. 57162
    Prev
    Next
    INDEX
    Explanations

    detection method, device, apparatus, technique, process, protocols

    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
    ergic
    -0.07
    èµ·è§ģ
    -0.07
    ola
    -0.06
    iban
    -0.06
    alainen
    -0.06
    tober
    -0.06
    verse
    -0.06
    ä¸įäºĨçļĦ
    -0.06
    rgan
    -0.06
    æĹłåĩł
    -0.06
    POSITIVE LOGITS
    两ä¸į误
    0.10
    æī«çłģåħ³æ³¨
    0.08
    undur
    0.08
    ×¢×ķת
    0.07
    ÏĢοι
    0.07
    ìĦ¸ìĬ¤
    0.07
     ulter
    0.07
    ä¸İæĸ¹æ³ķ
    0.07
    ñana
    0.07
    åĴĮæĸ¹æ³ķ
    0.07
    Activations Density 0.746%

    No Known Activations