© 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. 12029
    Prev
    Next
    INDEX
    Explanations

    quote fragments

    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
    .files
    -0.08
    .classes
    -0.08
    çļĦä¸Ģé¢Ĺ
    -0.07
    åIJĦç±»
    -0.07
    .FILES
    -0.07
    гин
    -0.07
    ä¸ĬäºĨä¸Ģ
    -0.07
    ymm
    -0.07
    åħ¬ä»Ķ
    -0.07
     клаÑģÑģов
    -0.07
    POSITIVE LOGITS
     fragment
    0.12
     excerpt
    0.11
    çīĩ段
    0.11
    åĩºèĩª
    0.11
     excerpts
    0.11
     fragments
    0.10
    åĩºå¤Ħ
    0.09
     snippet
    0.09
     passages
    0.09
    段èIJ½
    0.09
    Activations Density 0.100%

    No Known Activations