© 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. 2869
    Prev
    Next
    INDEX
    Explanations

    sensor detection

    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
    ä¸įæ±Ĥ
    -0.07
    讨
    -0.07
    ì¤Ģ
    -0.07
    ackle
    -0.07
    VERBOSE
    -0.07
    èĻ±
    -0.07
    éļ¾æ±Ĥ
    -0.07
     preserves
    -0.07
    iscard
    -0.07
     OMX
    -0.07
    POSITIVE LOGITS
     detecting
    0.13
     detects
    0.13
     Detect
    0.13
     monitoring
    0.13
    çĽijæµĭ
    0.13
     detection
    0.12
     monitor
    0.12
     detected
    0.12
    -trigger
    0.12
    çĽijè§Ĩ
    0.12
    Activations Density 0.267%

    No Known Activations