© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29686
    Prev
    Next
    INDEX
    Explanations

    non-destructive inspection and 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
    空æ°ĶåĩĢåĮĸåĻ¨
    -0.08
    èĨ³é£Ł
    -0.07
    èIJ¥åħ»ç´ł
    -0.07
    濯
    -0.07
    æ¡
    -0.07
    榨
    -0.07
    秫
    -0.07
     incomes
    -0.07
    åİī
    -0.07
     Dietary
    -0.06
    POSITIVE LOGITS
     detection
    0.11
     detecting
    0.11
     Detect
    0.11
     inspection
    0.11
    å¤įæ£Ģ
    0.11
     inspections
    0.10
     Detection
    0.10
    æ£Ģæµĭ
    0.10
     detections
    0.10
    æ£Ģæµĭ设å¤ĩ
    0.10
    Activations Density 0.060%

    No Known Activations