© 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. 57092
    Prev
    Next
    INDEX
    Explanations

    propagation and annihilation

    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
    éĵ¿
    -0.07
    rypton
    -0.07
    aises
    -0.07
    ahari
    -0.07
    翱
    -0.07
    èĢĮéĻį
    -0.07
     Brend
    -0.07
    å¿ĹåĪļ
    -0.07
     Guest
    -0.06
    建å®ī
    -0.06
    POSITIVE LOGITS
     propagation
    0.10
     propag
    0.09
    Propagation
    0.08
    ä¼łæĴŃ
    0.08
     propagate
    0.08
    ä¼łå¯¼
    0.08
    æī©æķ£
    0.08
    åįķåIJij
    0.08
    çļĦä¼łæĴŃ
    0.08
    åıªè¦ģæľī
    0.07
    Activations Density 0.003%

    No Known Activations