© 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. 14560
    Prev
    Next
    INDEX
    Explanations

    measuring and measurement

    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
    層
    -0.08
    å±Ĥ
    -0.08
     Ahead
    -0.08
    å±ĤçļĦ
    -0.08
    Inject
    -0.07
    顶å±Ĥ
    -0.07
     tér
    -0.07
    åı¯ä»¥çIJĨ解
    -0.07
     layer
    -0.07
    -layer
    -0.07
    POSITIVE LOGITS
    æµĭéĩı
    0.19
     measurement
    0.18
    æµĭéĩıçļĦ
    0.16
     measurements
    0.16
    measurement
    0.16
     measuring
    0.15
    Measurement
    0.15
     Measurement
    0.15
    測éĩı
    0.15
    ä¸Īéĩı
    0.13
    Activations Density 0.118%

    No Known Activations