© 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. 48534
    Prev
    Next
    INDEX
    Explanations

    sensitive detection limits

    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
    ÙĨدÛĮ
    -0.08
     Gord
    -0.08
    ä¾Ľå¤§å®¶
    -0.07
    æ°´çģ«
    -0.07
    ifix
    -0.07
    æĹłæļĩ
    -0.07
    åIJİå¸Ĥ
    -0.07
     Eure
    -0.07
    undy
    -0.07
    izer
    -0.07
    POSITIVE LOGITS
    微弱
    0.13
     detection
    0.10
     detect
    0.10
    å¾®å°ı
    0.09
     detecting
    0.09
    detect
    0.09
    çģµæķı度
    0.09
     Detection
    0.09
    çģµæķı
    0.09
     Detect
    0.08
    Activations Density 0.108%

    No Known Activations